gpt-4o-2024-05-13 v3 Evaluation

Generated: 2026-07-25 12:52:40 UTC

Pairs100
Distinct lemmas100
Slope0.880
R^20.913
BLEU-441.5%
chrF++66.9%
METEOR72.7%
ROUGE-L74.3%
BERTScoreN/A
COMETN/A
BLEURTN/A

Profile version id: 2406

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-4o (2024-05-13) 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
Slope0.880
Intercept3.606
R^20.913
P-value9.98e-54
Pearson r0.955
Mean source words30.400
Length fallback rows0
Mean human words44.160
Mean AI words42.460
Mean absolute length residual4.433
Mean absolute percent error8.5%

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 = -0.319, R^2 = 0.102, p = 0.0012.
chrF++ vs passage length
chrF++: significant negative; r = -0.377, R^2 = 0.142, p = 0.0001.
METEOR vs passage length
METEOR: significant negative; r = -0.445, R^2 = 0.198, p = 3.51e-06.
ROUGE-L vs passage length
ROUGE-L: significant negative; r = -0.443, R^2 = 0.196, p = 3.95e-06.
Trigram precision vs passage length
Trigram precision: significant negative; r = -0.301, R^2 = 0.091, p = 0.0024.
Trigram recall vs passage length
Trigram recall: significant negative; r = -0.323, R^2 = 0.105, p = 0.0010.
Trigram F1 vs passage length
Trigram F1: significant negative; r = -0.315, R^2 = 0.099, p = 0.0014.
Trigram Jaccard vs passage length
Trigram Jaccard: significant negative; r = -0.318, R^2 = 0.101, p = 0.0013.
Metric Rows Pattern Pearson r R^2 P-value Slope Status
BLEU-4 100 significant negative -0.319 0.102 0.0012 -0.00223 ok
chrF++ 100 significant negative -0.377 0.142 0.0001 -0.00174 ok
METEOR 100 significant negative -0.445 0.198 3.51e-06 -0.00250 ok
ROUGE-L 100 significant negative -0.443 0.196 3.95e-06 -0.00225 ok
BERTScore 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
COMET 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
BLEURT 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
Trigram precision 100 significant negative -0.301 0.091 0.0024 -0.00275 ok
Trigram recall 100 significant negative -0.323 0.105 0.0010 -0.00292 ok
Trigram F1 100 significant negative -0.315 0.099 0.0014 -0.00286 ok
Trigram Jaccard 100 significant negative -0.318 0.101 0.0013 -0.00293 ok

Translation Similarity Metrics

Mean BLEU-441.5%
Mean chrF++66.9%
Mean METEOR72.7%
Mean ROUGE-L74.3%
Mean BERTScoreN/A
Mean COMETN/A
Mean BLEURTN/A
Legacy smoothed corpus BLEU42.9%
Unigram F174.8%
Bigram F149.8%
Trigram precision36.9%
Trigram recall35.4%
Trigram F136.1%
Trigram Jaccard22.0%
4-gram F127.1%

Largest Length Residuals

Lemma ID Headword Human words AI words Residual BLEU-4 chrF++ METEOR ROUGE-L BERTScore COMET BLEURT Human Run Model
2468 Καπετώλιον 138 32 -93.026 0.3% 14.4% 12.9% 20.0% N/A N/A N/A reviewed/approved 13573 gpt-4o-2024-05-13
3288 Κορώνεια 110 126 25.610 32.4% 63.6% 63.7% 65.0% N/A N/A N/A reviewed/approved 13645 gpt-4o-2024-05-13
2603 Κάρυστος 175 176 18.420 32.6% 62.3% 64.6% 63.8% N/A N/A N/A reviewed/approved 13594 gpt-4o-2024-05-13
2604 Καρχηδών 117 123 16.451 35.3% 63.4% 65.1% 71.4% N/A N/A N/A reviewed/approved 13597 gpt-4o-2024-05-13
2119 Κάλλατις 65 74 13.204 18.6% 52.6% 56.2% 56.1% N/A N/A N/A reviewed/approved 13522 gpt-4o-2024-05-13
7254 Κύτα 84 90 12.487 37.2% 65.8% 67.1% 66.7% N/A N/A N/A reviewed/approved 13693 gpt-4o-2024-05-13
2326 Καλλίαρος 47 57 12.041 37.4% 68.1% 74.0% 73.1% N/A N/A N/A reviewed/approved 13528 gpt-4o-2024-05-13
7258 Κύτωρος 30 39 8.999 34.3% 70.3% 67.7% 66.7% N/A N/A N/A reviewed/approved 13705 gpt-4o-2024-05-13
7260 Κυχρεῖος πάγος 61 66 8.723 40.2% 65.4% 72.5% 64.6% N/A N/A N/A reviewed/approved 13711 gpt-4o-2024-05-13
2342 Κάμιρος 54 58 6.882 33.7% 66.1% 79.1% 76.8% N/A N/A N/A reviewed/approved 13558 gpt-4o-2024-05-13
2328 Καλλίπολις 43 48 6.561 42.8% 66.6% 73.3% 68.1% N/A N/A N/A reviewed/approved 13534 gpt-4o-2024-05-13
2055 Καβασσός 109 93 -6.510 33.5% 58.1% 60.7% 65.3% N/A N/A N/A reviewed/approved 13438 gpt-4o-2024-05-13
2465 Κάνωπος 83 83 6.366 39.3% 62.9% 81.3% 78.3% N/A N/A N/A reviewed/approved 13570 gpt-4o-2024-05-13
7248 Κύρου πόλις 32 38 6.239 10.2% 55.2% 54.9% 57.1% N/A N/A N/A reviewed/approved 13675 gpt-4o-2024-05-13
7255 Κυτέριον 22 29 6.038 30.6% 62.5% 64.7% 66.7% N/A N/A N/A reviewed/approved 13696 gpt-4o-2024-05-13
7266 Κώμη 79 79 5.886 14.1% 46.5% 47.8% 41.8% N/A N/A N/A reviewed/approved 13729 gpt-4o-2024-05-13
7259 Κύφος 54 57 5.882 27.6% 63.7% 67.5% 70.3% N/A N/A N/A reviewed/approved 13708 gpt-4o-2024-05-13
2484 Καρία 270 247 5.833 28.3% 57.8% 53.5% 58.8% N/A N/A N/A reviewed/approved 13582 gpt-4o-2024-05-13
7249 Κύρρος 45 49 5.801 40.5% 62.8% 75.8% 70.2% N/A N/A N/A reviewed/approved 13678 gpt-4o-2024-05-13
7251 Κύρτος 66 56 -5.676 28.6% 48.8% 63.3% 62.9% N/A N/A N/A reviewed/approved 13684 gpt-4o-2024-05-13
7247 Κύρνος 50 42 -5.598 16.4% 48.1% 54.4% 52.2% N/A N/A N/A reviewed/approved 13672 gpt-4o-2024-05-13
2470 Καππαδοκία 68 69 5.564 24.2% 64.3% 77.1% 75.9% N/A N/A N/A reviewed/approved 13576 gpt-4o-2024-05-13
2602 Καρύανδα 34 28 -5.521 30.0% 63.8% 74.9% 77.4% N/A N/A N/A reviewed/approved 13591 gpt-4o-2024-05-13
2599 Καρπήσιοι 11 8 -5.284 16.8% 49.9% 52.6% 63.2% N/A N/A N/A reviewed/approved 13588 gpt-4o-2024-05-13
7257 Κυτώνιον 25 21 -4.602 66.1% 75.8% 80.7% 87.0% N/A N/A N/A reviewed/approved 13702 gpt-4o-2024-05-13
2077 Καιρή 17 14 -4.563 44.7% 61.5% 53.4% 64.5% N/A N/A N/A reviewed/approved 13477 gpt-4o-2024-05-13
7253 Κυρτώνιος 18 15 -4.443 43.3% 69.8% 78.2% 84.8% N/A N/A N/A reviewed/approved 13690 gpt-4o-2024-05-13
2621 Κάστνιον 25 30 4.398 41.9% 72.2% 75.2% 76.4% N/A N/A N/A reviewed/approved 13612 gpt-4o-2024-05-13
2627 Κατάνειρα 21 18 -4.083 23.6% 63.8% 70.4% 82.1% N/A N/A N/A reviewed/approved 13627 gpt-4o-2024-05-13
2075 Καινίνη 15 13 -3.803 42.6% 69.2% 73.6% 78.6% N/A N/A N/A reviewed/approved 13468 gpt-4o-2024-05-13

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: 11.938; cross-validated R^2: -0.119.

Positive termCoefficientDocsMean presentMean absent
και 2.1353 66 0.504 -0.978
απο 1.6502 27 5.539 -2.049
δε και 1.0323 8 9.514 -0.827
ου 0.9188 14 4.572 -0.744
τη 0.8544 15 3.994 -0.705
οι 0.8232 11 6.328 -0.782
στραβων 0.8162 15 4.613 -0.814
πολιτης 0.7965 18 4.976 -1.092
εστι 0.7725 24 3.102 -0.980
πολις 0.7288 68 1.218 -2.588
παρα 0.7062 7 5.866 -0.442
την 0.7049 13 -1.067 0.159
εστι δε και 0.6814 3 14.541 -0.450
θηλυκον 0.6472 12 4.250 -0.580
βοιωτιας 0.6450 3 8.033 -0.248
λεγεται 0.5999 9 6.684 -0.661
λεγεται και 0.5961 8 7.324 -0.637
της 0.5819 35 -0.133 0.072
εν τη 0.5645 7 4.750 -0.358
εκαλειτο δε 0.5517 3 13.568 -0.420
Negative termCoefficientDocsMean presentMean absent
γαρ -3.0904 9 -6.499 0.643
δια του -1.8995 10 -5.433 0.604
του -1.6455 37 0.927 -0.545
δια -1.4370 16 -2.173 0.414
ζευς -1.0703 3 -28.849 0.892
αι -0.9954 3 -29.248 0.905
ηρωδιανος -0.9725 3 -28.678 0.887
ωστε -0.9397 3 -25.069 0.775
δε της -0.8757 6 -13.639 0.871
εξ -0.7781 3 -25.380 0.785
φησιν -0.7363 10 -7.211 0.801
τα -0.6717 12 -6.347 0.866
ειναι -0.6365 8 -9.396 0.817
το -0.6022 70 -0.251 0.585
τω -0.6013 16 -4.836 0.921
θεοπομπος -0.5308 5 -3.111 0.164
το εθνικον -0.4855 56 -1.073 1.366
εθνικον -0.4855 56 -1.073 1.366
περι -0.4682 11 -6.722 0.831
δε -0.4524 46 0.301 -0.257

Greek source terms predicting large absolute residuals

Features: 176; ridge alpha: 5.878; cross-validated R^2: -0.595.

Positive termCoefficientDocsMean presentMean absent
γαρ 6.1777 9 16.798 3.210
του 3.9134 37 7.823 2.443
δια του 3.6615 10 13.844 3.388
δια 3.0049 16 10.903 3.201
την 2.7960 13 15.038 2.849
εις 2.2957 7 23.163 3.024
ος 2.1963 6 23.029 3.246
εξ 2.1256 3 36.637 3.437
δε 2.1227 46 6.307 2.837
εν 2.0066 37 7.341 2.726
ωστε 1.8587 3 37.349 3.415
ειναι 1.8534 8 16.888 3.350
αι 1.8501 3 33.837 3.524
ζευς 1.8469 3 33.168 3.545
ηρωδιανος 1.6877 3 33.339 3.539
δε της 1.6638 6 20.604 3.401
περι 1.3376 11 13.523 3.310
τα 1.0293 12 11.752 3.435
της 0.9647 35 7.337 2.870
τω 0.9517 16 9.868 3.398
Negative termCoefficientDocsMean presentMean absent
ως -1.4677 52 3.473 5.474
το εθνικον -0.9234 56 4.777 3.996
εθνικον -0.9234 56 4.777 3.996
προς τη -0.8832 4 0.911 4.580
οικητωρ -0.8023 6 2.774 4.539
ηροδοτος -0.7986 9 2.559 4.619
τον -0.7674 10 4.247 4.454
τους -0.7152 4 2.211 4.526
τινες -0.6959 6 1.788 4.602
νησος -0.6815 9 2.502 4.624
πολις -0.6094 68 3.838 5.699
ην -0.5960 13 3.658 4.549
δευτερω -0.5726 3 1.426 4.526
εκ -0.5521 6 3.207 4.512
και πολις -0.5471 5 1.907 4.566
τινες δε -0.5373 3 1.616 4.520
και του -0.5021 4 3.089 4.489
εκαταιος -0.4972 14 4.583 4.409
καππαδοκιας -0.4971 3 3.051 4.476
προς -0.4880 15 4.855 4.359

AI English terms predicting large absolute residuals

Features: 317; ridge alpha: 24.245; cross-validated R^2: -0.763.

Positive termCoefficientDocsMean presentMean absent
about 1.1934 3 31.395 3.599
called the 1.1696 4 24.884 3.581
that 0.9862 13 13.588 3.065
says 0.9747 8 14.828 3.529
to the 0.9588 10 13.146 3.465
the 0.9287 93 4.626 1.877
name 0.8031 13 10.912 3.465
to 0.7782 22 9.071 3.125
with 0.6989 17 9.048 3.488
called 0.6726 34 8.092 2.548
an 0.6345 17 8.705 3.558
of the 0.6146 28 7.871 3.097
of 0.4898 66 5.492 2.378
it 0.4806 42 7.115 2.492
and 0.3495 52 6.132 2.593
form 0.2651 17 7.317 3.843
from the form 0.2206 4 10.970 4.161
the form 0.2206 4 10.970 4.161
the son 0.1610 13 9.148 3.729
the son of 0.1610 13 9.148 3.729
Negative termCoefficientDocsMean presentMean absent
the ethnonym -0.3835 56 3.232 5.962
ethnonym -0.3808 56 3.232 5.962
the ethnonym is -0.3756 53 3.036 6.009
ethnonym is -0.3756 53 3.036 6.009
is -0.3708 89 3.645 10.816
as -0.3049 60 3.757 5.447
a city -0.2968 66 3.934 5.403
just as -0.2788 13 1.707 4.841
just -0.2788 13 1.707 4.841
book -0.2673 41 3.066 5.384
a city in -0.2658 41 3.716 4.932
city in -0.2366 42 3.654 4.997
in the -0.2285 20 3.484 4.671
as in -0.1829 20 3.404 4.691
island -0.1825 14 2.721 4.712
in his -0.1769 24 3.863 4.613
an island -0.1732 9 2.156 4.659
book the -0.1721 11 2.570 4.664
his -0.1694 34 4.015 4.649
people -0.1620 12 3.320 4.585

Human English terms predicting large absolute residuals

Features: 336; ridge alpha: 5.878; cross-validated R^2: -0.632.

Positive termCoefficientDocsMean presentMean absent
with 6.2450 16 9.675 3.435
the 2.6332 90 4.714 1.910
on the 2.5622 10 12.171 3.574
sanctuary 2.5508 3 33.505 3.534
forms 2.4563 4 26.643 3.508
on 1.9894 16 9.177 3.530
from 1.7331 37 7.147 2.840
is 1.7309 87 4.676 2.808
it 1.6465 37 6.954 2.953
that 1.5630 29 7.848 3.039
at 1.4664 6 22.093 3.306
has 1.4051 6 23.612 3.209
and 1.3215 52 6.158 2.565
long 1.3127 3 34.915 3.491
this is 1.2147 4 26.652 3.508
diphthong 1.1833 3 33.336 3.539
is with 1.1559 4 28.938 3.412
zeus 1.1556 5 23.809 3.414
herodian 1.1431 3 33.339 3.539
so 1.1252 5 23.823 3.413
Negative termCoefficientDocsMean presentMean absent
as -1.5039 60 3.556 5.749
as in -0.8674 29 3.338 4.881
the ethnonym is -0.7620 52 4.729 4.113
ethnonym is -0.7620 52 4.729 4.113
near -0.7208 16 3.350 4.640
the ethnonym -0.7044 56 4.875 3.872
ethnonym -0.6919 57 4.903 3.810
an -0.6915 22 2.874 4.873
his -0.6455 34 3.722 4.800
island -0.6424 14 2.721 4.712
some -0.6384 10 3.082 4.584
herodotos -0.5601 9 2.559 4.619
book -0.5438 39 3.310 5.152
or after -0.5066 3 0.481 4.556
city in -0.4812 41 3.758 4.903
say that -0.4710 9 3.171 4.558
in his -0.4514 19 4.404 4.440
an island -0.4511 9 2.650 4.610
a city in -0.4354 40 3.823 4.840
ethnonyms -0.4287 3 2.772 4.485

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.