gpt-4-turbo-2024-04-09 v3 Evaluation

Generated: 2026-09-20 11:20:55 UTC

Pairs100
Distinct lemmas100
Slope0.921
R^20.976
BLEU-435.8%
chrF++63.1%
METEOR68.3%
ROUGE-L68.8%
BERTScore94.4%
COMET77.0%
BLEURT70.1%

Profile version id: 2403

First translation using this version: 2026-07-16

Total usable AI runs for this version: 100 runs across 100 lemmas

Created: 2026-07-16 06:54:03.500756+10:00

Active: True

Notes: Model timeline evaluation: GPT-4 Turbo (2024-04-09) using prompt text from gpt-5.5 v3; approved-human-only for the 100-row Kappa corpus.

Prompt length scatter plot

Length Regression

FormulaAI words = intercept + slope * human words
Slope0.921
Intercept3.606
R^20.976
P-value3.65e-81
Pearson r0.988
Mean source words30.400
Length fallback rows0
Mean human words44.150
Mean AI words44.250
Mean absolute length residual4.121
Mean absolute percent error9.9%

Metric vs Passage Length

These plots test whether score changes with source passage length for this prompt version. The dashed line is an ordinary least-squares fit; the annotation reports n, r, R^2, p-value, and slope.

BLEU-4 vs passage length
BLEU-4: significant negative; r = -0.353, R^2 = 0.125, p = 0.0003.
chrF++ vs passage length
chrF++: significant negative; r = -0.345, R^2 = 0.119, p = 0.0004.
METEOR vs passage length
METEOR: significant negative; r = -0.462, R^2 = 0.213, p = 1.31e-06.
ROUGE-L vs passage length
ROUGE-L: significant negative; r = -0.440, R^2 = 0.194, p = 4.55e-06.
BERTScore vs passage length
BERTScore: significant negative; r = -0.506, R^2 = 0.256, p = 7.82e-08.
COMET vs passage length
COMET: significant negative; r = -0.339, R^2 = 0.115, p = 0.0006.
BLEURT vs passage length
BLEURT: significant negative; r = -0.743, R^2 = 0.552, p = 8.73e-19.
Trigram precision vs passage length
Trigram precision: significant negative; r = -0.316, R^2 = 0.100, p = 0.0014.
Trigram recall vs passage length
Trigram recall: significant negative; r = -0.345, R^2 = 0.119, p = 0.0004.
Trigram F1 vs passage length
Trigram F1: significant negative; r = -0.330, R^2 = 0.109, p = 0.0008.
Trigram Jaccard vs passage length
Trigram Jaccard: significant negative; r = -0.329, R^2 = 0.108, p = 0.0008.
Metric Rows Pattern Pearson r R^2 P-value Slope Status
BLEU-4 100 significant negative -0.353 0.125 0.0003 -0.00202 ok
chrF++ 100 significant negative -0.345 0.119 0.0004 -0.00133 ok
METEOR 100 significant negative -0.462 0.213 1.31e-06 -0.00227 ok
ROUGE-L 100 significant negative -0.440 0.194 4.55e-06 -0.00195 ok
BERTScore 100 significant negative -0.506 0.256 7.82e-08 -0.00043 ok
COMET 100 significant negative -0.339 0.115 0.0006 -0.00063 ok
BLEURT 100 significant negative -0.743 0.552 8.73e-19 -0.00244 ok
Trigram precision 100 significant negative -0.316 0.100 0.0014 -0.00207 ok
Trigram recall 100 significant negative -0.345 0.119 0.0004 -0.00221 ok
Trigram F1 100 significant negative -0.330 0.109 0.0008 -0.00213 ok
Trigram Jaccard 100 significant negative -0.329 0.108 0.0008 -0.00172 ok

Translation Similarity Metrics

Mean BLEU-435.8%
Mean chrF++63.1%
Mean METEOR68.3%
Mean ROUGE-L68.8%
Mean BERTScore94.4%
Mean COMET77.0%
Mean BLEURT70.1%
Legacy smoothed corpus BLEU36.1%
Unigram F170.0%
Bigram F142.5%
Trigram precision28.3%
Trigram recall28.4%
Trigram F128.4%
Trigram Jaccard16.5%
4-gram F120.1%

Largest Length Residuals

Lemma ID Headword Human words AI words Residual BLEU-4 chrF++ METEOR ROUGE-L BERTScore COMET BLEURT Human Run Model
3288 Κορώνεια 110 130 25.129 27.3% 59.5% 63.1% 61.4% 92.4% 72.6% 59.1% reviewed/approved 12446 gpt-4-turbo-2024-04-09
2342 Κάμιρος 54 68 14.682 35.4% 66.6% 67.9% 67.2% 93.6% 75.7% 62.2% reviewed/approved 12359 gpt-4-turbo-2024-04-09
2484 Καρία 270 238 -14.167 18.8% 50.6% 45.9% 50.4% 88.6% 76.5% 41.2% reviewed/approved 12383 gpt-4-turbo-2024-04-09
7254 Κύτα 84 95 14.064 31.9% 63.9% 69.8% 64.8% 92.9% 77.3% 57.6% reviewed/approved 12494 gpt-4-turbo-2024-04-09
2055 Καβασσός 109 92 -11.951 22.5% 53.3% 51.8% 52.7% 93.1% 75.8% 51.1% reviewed/approved 12239 gpt-4-turbo-2024-04-09
2470 Καππαδοκία 68 78 11.794 7.0% 47.6% 51.2% 58.9% 93.2% 72.6% 58.7% reviewed/approved 12377 gpt-4-turbo-2024-04-09
2621 Κάστνιον 25 38 11.379 38.9% 67.8% 65.6% 60.3% 94.9% 69.2% 72.7% reviewed/approved 12413 gpt-4-turbo-2024-04-09
2597 Καρπασία 112 117 10.287 32.9% 62.2% 58.7% 60.3% 94.1% 75.5% 56.2% reviewed/approved 12386 gpt-4-turbo-2024-04-09
7257 Κυτώνιον 25 17 -9.621 22.7% 47.2% 48.7% 57.1% 92.7% 74.8% 61.7% reviewed/approved 12503 gpt-4-turbo-2024-04-09
2119 Κάλλατις 65 73 9.556 12.6% 52.3% 55.2% 52.2% 92.3% 65.3% 53.6% reviewed/approved 12323 gpt-4-turbo-2024-04-09
2609 Κάσπειρος 135 119 -8.886 28.7% 56.5% 51.4% 59.8% 88.5% 72.1% 61.7% reviewed/approved 12407 gpt-4-turbo-2024-04-09
7258 Κύτωρος 30 40 8.776 34.2% 65.1% 57.5% 57.1% 93.0% 75.2% 75.2% reviewed/approved 12506 gpt-4-turbo-2024-04-09
2465 Κάνωπος 83 72 -8.015 28.7% 57.8% 64.5% 69.7% 93.6% 73.7% 64.2% reviewed/approved 12371 gpt-4-turbo-2024-04-09
2604 Καρχηδών 117 119 7.684 23.1% 54.3% 53.3% 53.8% 92.6% 76.6% 56.9% reviewed/approved 12398 gpt-4-turbo-2024-04-09
7251 Κύρτος 66 57 -7.365 31.7% 56.2% 61.7% 66.1% 92.6% 72.0% 65.2% reviewed/approved 12485 gpt-4-turbo-2024-04-09
2624 Κατάβαθμος 20 29 6.982 34.0% 61.3% 65.5% 57.1% 92.4% 79.0% 75.9% reviewed/approved 12422 gpt-4-turbo-2024-04-09
7250 Κυρταία 40 47 6.570 39.6% 64.6% 65.7% 59.8% 93.9% 74.6% 71.0% reviewed/approved 12482 gpt-4-turbo-2024-04-09
2054 Καβαλίς 65 70 6.556 33.4% 61.5% 53.6% 60.7% 93.3% 73.9% 64.7% reviewed/approved 12236 gpt-4-turbo-2024-04-09
2116 Κάληρος 40 34 -6.430 20.2% 49.8% 47.0% 54.1% 91.5% 72.5% 67.2% reviewed/approved 12314 gpt-4-turbo-2024-04-09
7255 Κυτέριον 22 30 6.141 23.9% 55.1% 55.4% 61.5% 94.3% 74.9% 73.3% reviewed/approved 12497 gpt-4-turbo-2024-04-09
2623 Κασώριον 20 28 5.982 11.9% 44.4% 48.3% 50.0% 90.4% 70.4% 60.1% reviewed/approved 12419 gpt-4-turbo-2024-04-09
3496 Κοτιάειον 71 63 -5.968 17.4% 47.8% 53.7% 50.7% 93.4% 72.9% 65.4% reviewed/approved 12449 gpt-4-turbo-2024-04-09
2602 Καρύανδα 34 29 -5.906 41.5% 65.9% 72.2% 66.7% 96.1% 77.9% 74.3% reviewed/approved 12392 gpt-4-turbo-2024-04-09
2605 Κάσιον 56 61 5.841 30.4% 60.4% 61.8% 63.2% 93.2% 75.1% 64.8% reviewed/approved 12401 gpt-4-turbo-2024-04-09
2056 Καβειρία 112 101 -5.713 30.9% 68.2% 69.7% 66.7% 95.3% 80.0% 62.2% reviewed/approved 12242 gpt-4-turbo-2024-04-09
2468 Καπετώλιον 138 125 -5.648 12.5% 47.0% 48.0% 50.0% 87.2% 66.5% 49.1% reviewed/approved 12374 gpt-4-turbo-2024-04-09
2115 Καλὴ ἀκτή 64 68 5.476 18.1% 56.2% 57.3% 56.1% 91.6% 71.6% 58.9% reviewed/approved 12311 gpt-4-turbo-2024-04-09
7260 Κυχρεῖος πάγος 61 65 5.238 41.9% 63.2% 60.9% 60.3% 93.6% 74.5% 61.4% reviewed/approved 12512 gpt-4-turbo-2024-04-09
2078 Καινύς 22 19 -4.859 49.6% 65.6% 68.5% 73.2% 94.5% 81.8% 76.7% reviewed/approved 12275 gpt-4-turbo-2024-04-09
2455 Κάναστρον 60 54 -4.841 19.0% 52.3% 57.5% 66.7% 93.9% 72.6% 64.3% reviewed/approved 12368 gpt-4-turbo-2024-04-09

Residual Predictors

Positive signed-residual terms are associated with AI translations longer than expected from the human length; negative signed-residual terms are associated with shorter AI translations. Absolute-residual models identify terms associated with larger AI-human length divergence.

Greek source terms predicting signed length residuals

Features: 176; ridge alpha: 2.894; cross-validated R^2: -0.053.

Positive termCoefficientDocsMean presentMean absent
την 3.2037 13 3.037 -0.454
ου 2.7938 14 3.910 -0.636
εις 2.7520 7 5.719 -0.430
πολιτης 2.3399 18 5.354 -1.175
και 2.3085 66 0.832 -1.616
ου και 2.0191 4 8.394 -0.350
εν τη 1.9972 7 5.360 -0.403
θηλυκως 1.9121 5 6.565 -0.346
και θηλυκως 1.9121 5 6.565 -0.346
λεγεται 1.7744 9 4.484 -0.444
εστι δε και 1.7053 3 11.874 -0.367
λεγεται και 1.7041 8 4.694 -0.408
εξ 1.6758 3 6.598 -0.204
απο 1.6667 27 2.881 -1.065
βοιωτιας 1.6585 3 5.318 -0.164
παιδος 1.6505 4 6.987 -0.291
εστι δε 1.6306 5 7.077 -0.372
δε και 1.5584 8 3.527 -0.307
απο του 1.4463 9 4.595 -0.454
τοις 1.3059 3 7.926 -0.245
Negative termCoefficientDocsMean presentMean absent
τω -2.6866 16 -2.741 0.522
το -2.1671 70 0.105 -0.245
καππαδοκιας -2.0848 3 -6.053 0.187
τα -1.9362 12 -3.479 0.474
γαρ -1.8909 9 -2.102 0.208
ουτως -1.8085 5 -7.312 0.385
θεοπομπος -1.7717 5 -1.842 0.097
εκαλειτο -1.4764 7 -3.554 0.267
εν τω -1.4371 6 -4.258 0.272
ως το -1.3710 3 -8.343 0.258
περι -1.2806 11 -2.523 0.312
τω περι -1.2202 4 -6.495 0.271
εν τω περι -1.2202 4 -6.495 0.271
εθνος -1.2160 8 -2.526 0.220
μεν -1.1062 4 -6.391 0.266
το εθνικον -1.0953 56 -0.956 1.217
εθνικον -1.0953 56 -0.956 1.217
μετα -0.9722 3 -7.372 0.228
τινες -0.9720 6 -2.191 0.140
θρακης -0.9468 5 -3.017 0.159

Greek source terms predicting large absolute residuals

Features: 176; ridge alpha: 2.031; cross-validated R^2: -0.061.

Positive termCoefficientDocsMean presentMean absent
την 4.0579 13 7.924 3.553
ου 2.9122 14 7.832 3.517
εις 2.8783 7 11.380 3.575
μεταξυ 2.7563 5 11.435 3.737
βοιωτιας 2.2402 3 11.434 3.895
δε 2.1538 46 5.674 2.799
δυναται 1.9344 3 14.407 3.803
και 1.9234 66 4.863 2.681
απο 1.6228 27 6.647 3.187
εδει 1.5969 3 9.427 3.957
απο του 1.5337 9 7.575 3.780
εξ 1.5302 3 10.364 3.928
θηλυκον 1.4831 12 6.619 3.781
γαρ 1.4781 9 7.990 3.739
παρα 1.4623 7 8.099 3.822
πολις εν 1.3485 5 8.298 3.902
εν 1.3335 37 5.669 3.213
ου και 1.3290 4 8.394 3.943
θεοπομπος 1.3013 5 5.957 4.025
ος 1.1825 6 8.399 3.848
Negative termCoefficientDocsMean presentMean absent
τους -1.4399 4 1.452 4.233
το εθνικον -1.3748 56 3.546 4.854
εθνικον -1.3748 56 3.546 4.854
μια -1.3611 3 0.481 4.234
και το -1.1040 9 3.789 4.154
των -1.0685 17 4.337 4.077
τον -0.9719 10 3.594 4.180
ιβηριας -0.9345 3 3.128 4.152
προς τη -0.9002 4 2.302 4.197
το -0.8996 70 4.332 3.631
και πολις -0.8685 5 3.019 4.179
ης -0.8590 3 2.566 4.170
στραβων -0.8569 15 3.821 4.175
πολυβιος -0.8122 5 1.838 4.242
παυσανιας -0.8114 4 3.091 4.164
δια το -0.7796 3 2.155 4.182
μητροπολις -0.7369 3 3.404 4.144
ουδετερως -0.6874 3 1.916 4.190
πλησιον -0.6585 8 3.252 4.197
δευτερω -0.6468 3 2.055 4.185

AI English terms predicting large absolute residuals

Features: 350; ridge alpha: 1.425; cross-validated R^2: -0.078.

Positive termCoefficientDocsMean presentMean absent
to 3.4939 30 6.421 3.136
from 3.3490 40 5.695 3.073
between 2.6733 6 11.495 3.651
those 2.6485 5 11.689 3.723
this 2.4031 10 7.175 3.782
name 2.2656 7 8.456 3.795
and in 2.1920 4 10.818 3.842
into 1.9651 3 13.071 3.845
boeotia 1.8793 3 11.434 3.895
in the feminine 1.7744 3 10.005 3.940
and 1.7233 55 5.361 2.607
the feminine 1.6794 13 7.083 3.679
for 1.6615 10 7.366 3.761
it 1.6427 40 5.512 3.195
situated 1.5687 4 12.414 3.776
feminine 1.5644 16 6.606 3.648
mentioned 1.5137 6 9.960 3.749
from the 1.4530 12 7.610 3.646
be 1.4361 16 7.338 3.509
from which also 1.4231 3 10.069 3.938
Negative termCoefficientDocsMean presentMean absent
the ethnonym -1.3569 55 3.637 4.714
they -1.2958 8 3.863 4.144
is named -1.2676 6 2.410 4.231
the ethnonym is -1.1853 51 3.672 4.590
because -1.1784 7 2.695 4.229
a city of -1.0586 10 2.621 4.288
because the -1.0301 4 1.510 4.230
arcadia -1.0245 3 1.165 4.213
ethnonym -1.0117 57 3.778 4.576
mount -0.9796 3 1.579 4.200
there is another -0.9790 3 1.726 4.196
is another -0.9790 3 1.726 4.196
also a city -0.8596 7 3.671 4.155
as in -0.8500 18 3.973 4.154
is called -0.8456 20 4.940 3.917
ethnonym is -0.8287 53 3.822 4.459
town -0.8248 5 3.108 4.175
per -0.8179 32 4.725 3.837
as per -0.8179 32 4.725 3.837
pausanias -0.8083 4 3.091 4.164

Human English terms predicting large absolute residuals

Features: 335; ridge alpha: 1.425; cross-validated R^2: -0.085.

Positive termCoefficientDocsMean presentMean absent
between 2.7118 6 11.495 3.651
from 2.6117 37 5.865 3.097
boiotia 2.5123 3 11.434 3.895
however 2.4165 10 9.377 3.538
and 2.3805 52 5.317 2.827
is from 2.2974 12 7.139 3.710
who 1.8749 13 7.093 3.677
city on 1.8452 3 10.269 3.931
into 1.8330 3 13.071 3.845
also said 1.8327 6 10.277 3.729
said 1.8327 6 10.277 3.729
feminine 1.7666 16 6.606 3.648
the feminine 1.7666 16 6.606 3.648
the 1.7043 90 4.238 3.077
has 1.6385 6 9.971 3.748
also 1.6362 43 5.299 3.233
kappadokia 1.6044 4 7.488 3.981
be 1.5663 15 6.931 3.626
it should 1.5292 3 9.427 3.957
should 1.5292 3 9.427 3.957
Negative termCoefficientDocsMean presentMean absent
one of -1.6157 5 1.219 4.274
one of the -1.4926 4 0.596 4.268
mount -1.3185 4 1.204 4.243
either -1.1692 6 4.124 4.121
the ethnonym is -1.0991 52 3.628 4.656
ethnonym is -1.0991 52 3.628 4.656
the ethnonym -1.0691 56 3.677 4.687
are -1.0499 25 4.573 3.971
they -1.0102 12 5.477 3.937
near -0.9905 16 3.181 4.301
per -0.9877 20 4.185 4.106
as per -0.9877 20 4.185 4.106
and the -0.9763 15 4.115 4.123
as in -0.9176 29 4.354 4.027
ethnonym -0.9133 57 3.822 4.518
or after -0.8978 3 2.514 4.171
it used to -0.8777 3 1.531 4.202
it used -0.8777 3 1.531 4.202
when -0.8717 7 4.351 4.104
arkadia -0.8684 3 1.165 4.213

Prompt Text

Show prompt text
You are an expert classical philologist and translator specialising in Stephanos of Byzantium's Ethnika.

Goal
- Produce a clear, scholarly English translation in the established reviewed house style.
- Stay close to the Greek while making Stephanos' compressed reference-work prose intelligible in English.
- Translate the Greek main text of the entry, not the modern apparatus, editorial locators, or later bibliographic explanation.

Priority order
- Follow the source Greek first.
- Apply the output and formatting rules below.
- Apply any entry-specific Additional translation context supplied with the entry, but only where the cited Greek evidence is relevant.
- Do not force a rule, gloss, or proper-noun convention when the local syntax or context contradicts it.

Output rules (required)
- Respond ONLY by calling the submit_translation tool with a single string field: {"translation": "..."}.
- The translation text must contain only the translation.
- Do not include analysis, commentary, alternative translations, uncertainty notes, or Markdown outside the translation itself.

A) Formatting + spelling
- Use Australasian spelling and punctuation conventions.
- Preserve paragraphing and line-breaks when they are present in the Greek source.
- For verse quotations, preserve line segmentation in English where the Greek source marks or implies individual verse lines.
- For lengthy prose quotations that function as a quoted block, allow paragraph/quotation separation so the quotation remains readable. Do not create stanza-like line breaks for ordinary short prose snippets.
- Use single quotes for quoted forms, cited snippets, translated quotations, appellations derived from or pertaining to the headword (such as ethnonyms and similar gentilics, but not divine epithets), and Greek forms rendered in Latin letters: '...'.
- Avoid double quotes.
- Use *italics* for titles of ancient works when they are actual work titles: *Cypriaka*, *Bassarika*, *Europe*, *Periegesis*, *Geography*.
- Do not italicise descriptive phrases that are not work titles, such as an epitome of another author's books.

B) Opening / structure
- Let the Greek structure control the opening. Do not force every entry into a single template.
- When the entry opens with the headword and a brief identification, normally begin with the headword transliterated into Latin letters without Greek diacritics, followed by the identification.
- Typical form where appropriate: Headword: ...
- Appositive openings like 'Karia, the country.' are acceptable when the entry is of that type.
- If the headword line gives both nominative and genitive, render it compactly as 'X, Y: ...' unless a grammatical tag is needed for clarity.
- Keep numbered or lettered sequences of homonymous places as inline numbered items like (2) ... (3) ..., matching the Greek's structure.
- When Greek ἔστι καὶ ἄλλη / ἕτερος introduces another place with the same name, use 'There is also another ...' when that is needed for sense.
- For appositional settlement descriptions of the type X (proper noun) + Y (settlement noun) + Z (genitive territory), translate the territory as location: 'X, a city/town/village in Z', not 'of Z', unless the Greek clearly expresses possession, origin, descent, or another non-locative relationship.

C) Transliteration + naming
- Do NOT use macrons or acute accents in ordinary transliteration: Karystos, not Kárystos.
- Prefer Greek-form transliteration when Stephanos is discussing Greek forms, derivation, spelling, ethnonyms, or other metalinguistic material.
- Use these general correspondences unless an established house-style exception is supplied: η = e, κ = k, φ = ph, ῥ = rh, ῤ = r, υ = y, χ = ch.
- Use Greek-style transliteration of diphthongs, especially ai for αι. Do not drift into Latinised forms such as ae or e where the Greek form matters.
- Use forms such as Karchedon, Chalkedon, Kapetolion, Kyrene, Kyrtos, Kappadokia, and Palaistine in Greek-form contexts.
- Avoid Latinised forms such as Carthage, Chalcedon, Capitolium, Cyrene, Cyrtos, Cappadocia, and Palestine in Greek-form contexts.
- Use established conventional English forms only when they are house-style exceptions or clearly ordinary geography, for example Rome, Cyprus, Egypt, Syria, India, Sicily, Thebes, Peloponnese, the Black Sea, the Red Sea, and the Persian Gulf.
- Treat conventional English-name exceptions as a conservative whitelist. Do not expand it by analogy without entry-specific guidance.
- Keep Greek-form transliteration for most ethnonyms and derived adjectives, and put the cited form in single quotes.
- Do not Latinise river, people, or place names merely because a familiar Latin or English form exists.

D) Citations (authors/works/books)
- Translate only the citation information that is present in the original Greek words of the lemma entry.
- Ignore modern/editorial locator codes and apparatus-like add-ons: omit RE/SH numbers, FGrHist numbers, fragment numbers, chapter/section locators, column references, and parenthetical references such as (12,1,2 [C 533,12]), (Op. 344), or (A. R. 2,403).
- Do not infer a book number from a modern parenthetical reference.
- If the Greek says only 'Strabo' plus a modern parenthetical locator, translate 'Strabo', not 'Strabo, book 12'.
- Use 'as per X' only where the Greek itself has ὡς + author/name or an equivalent example-marker construction that supports that rendering.
- If the Greek explicitly gives a Greek book numeral, translate it: 'Ktesias in book 3 of his *Persika*'.
- Keep citations compact, mirroring the source's incompleteness:
  - Author + work title: 'Hellanikos in his *Cypriaka*'
  - Author + book: 'Pausanias, book 9.'
  - Author + work + book: 'Dionysios in book 3 of his *Bassarika*: ...'
- Work-title guidance:
  - Γεωγραφούμενα / γεωγραφικά in citation contexts -> *Geography*, not *Geographoumena*, when this is the established house treatment for the cited work.
  - Περιήγησις / Περίοδος should normally preserve the transmitted title as *Periegesis* when that is what Stephanos gives.
  - If the Greek says an author is cited in an epitome of the eleven books, do not italicise *Epitome* as a work title; translate 'in an epitome of his eleven books'.
- If a citation is present in the source as bracketed main text and later syntax depends on it, translate it in brackets rather than omitting it.
- Do not add external citation labels like Iliad, Works and Days, or Argonautica unless the Greek itself names them.

E) Entry-specific guidance context
- Additional translation context may be supplied for the current entry.
- This context can include matched formula rules, glossary rules, proper-noun conventions, contextual vocabulary bias, and external source passages.
- Apply required or replacement guidance strongly when the evidence matches the current Greek.
- Apply formula and gloss guidance according to the local syntax; do not make it mechanical if the context requires a different construction.
- Apply proper-noun guidance for consistency where supplied, but do not overwrite the Greek's grammatical point.
- Apply contextual vocabulary bias as a preference, not as a one-to-one replacement. It should steer the wording when the stated semantic context is present.
- Use external source passages only for quoted or allusive material. Do not replace Stephanos' own wording with the external source translation.
- Do not mention which guidance rules fired in the translation output. The review interface should surface that separately.

F) Philological, grammatical, and orthographic discussion
- When the entry discusses spelling, letters, diphthongs, accents, stress, case, gender, number, dialect, or morphology, preserve the technical claim precisely.
- Preserve Greek letters or digraphs in Greek script when the letter or digraph itself is under discussion, for example ι, ει, οι, υ.
- Prefer transliteration for cited word-forms unless the point depends on Greek spelling, accentuation, a specific letter, or a visible dialectal/prosodic distinction.
- If accentuation or prosody is the topic:
  - τόνος -> stress or accentuation, according to context.
  - ὀξύς describing a word's τόνος -> oxytone, not merely 'acute'.
  - βαρύς describing a word's τόνος -> barytone, not merely 'grave'.
  - Keep the form in a representation that makes the contrast visible. Use Greek script where the Greek spelling or accent is the point.
- When Stephanos cites an inflected form, dialectal form, or poetic form as evidence for another form, do not normalise away the form being demonstrated.
- If the cited form is inflected or dialectal, translate using the English lemma derived from the appropriate Greek nominative where that is needed for consistency. For example, treat Κυταιέος as evidence for Kytaieus from Κυταιεύς, not as a different nominative such as Kytaios.
- Use brief grammatical tags only when they are necessary to make the philological point visible:
  - case: (nom.), (acc.), (gen.), (dat.), (voc.)
  - gender: (m.), (f.), (n.)
  - number: (sing.), (pl.)

G) Comparisons / derivational analogies
- For ὡς + X where X is an analogous form or etymologically related noun, use a form like "(as in 'X')" where this makes the analogy clear.
- For fuller derivational analogies, keep the relation explicit:
  - as 'Byzantios' is from the name Byzantion
  - as in 'Lykaones', from Lykaonia
- Avoid bare 'like X' when the point is morphological analogy.

H) ἀπό, ἀφ' οὗ, and naming/derivation formulae
- If ἀπό + genitive gives an eponym or naming source, prefer 'after X' or 'named after X' rather than a flat 'from X'.
- In entries with temporal naming contrast, ἐκαλεῖτο X ... κέκληται Y -> 'It used to be called X; it is now called/named Y.'
- For ἀφ' οὗ:
  - With a masculine personal antecedent in a naming context, translate 'after whom'.
  - With an explicit neuter antecedent, translate 'from which'.
  - With a dropped neuter antecedent or Stephanos' example-marker usage, translate naturally according to the syntax; use 'as per' only when the Greek construction supports an evidentiary/example sense.
- Avoid archaic 'whence' unless it is clearly the most natural scholarly English.

I) Syntax and restraint
- Translate directly; do not add background explanation, modern bibliography, or parenthetical glosses unless Stephanos gives them.
- Do not add glosses like (synoikia), (kalathos), or explanatory etymologies unless the Greek explicitly defines the term.
- Avoid gratuitous adversatives for δέ.
- Use 'however' only for a real contrast, such as a correction, opposition, exception, or contrastive second item that English needs to mark.
- Avoid 'on the other hand' unless the Greek contrast is strong and English needs it.
- Convert participles into natural English when strict literalness obscures the structure.
- Circumstantial participles may need 'because', 'as', 'when', or a relative clause.
- Preserve uncertainty when the Greek is uncertain, corrupt, or genuinely ambiguous; do not invent a resolution.
- If the source includes bracketed or braced text as part of the lemma main Greek text of the Meineke edition rather than apparatus, translate it and keep brackets if that best reflects the source.
- If the source gives indirect speech under φασί, do not automatically turn it into a formal quotation unless the source punctuation or reference-work style calls for it.

Now translate the provided entry accordingly, and submit it via submit_translation.