Triple
T3662744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Marathon |
E77687
|
entity |
| Predicate | PersianCasualties |
P6773
|
FINISHED |
| Object | several thousand Persians killed |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: several thousand Persians killed | Statement: [Battle of Marathon, PersianCasualties, several thousand Persians killed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: PersianCasualties Context triple: [Battle of Marathon, PersianCasualties, several thousand Persians killed]
-
A.
militaryCasualtiesEstimate
chosen
Indicates an estimated number of people killed, wounded, or missing as a result of military conflict or operations.
-
B.
AfghanCasualties
Indicates the number or occurrence of casualties suffered by Afghan individuals or forces in a given event or context.
-
C.
nativeCasualties
Indicates that native or indigenous people suffered deaths or injuries as a result of a particular event, action, or conflict.
-
D.
PolishCasualties
Indicates the number or extent of casualties suffered by Polish forces or population in a given conflict or event.
-
E.
PersianCommander
Indicates that an entity serves as a military commander for, or in the context of, the Persian forces or Persian polity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ad85dfc4dc8190a441864202ab2a7a |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3fcd910819082012b10b23860aa |
completed | March 8, 2026, 6:46 p.m. |
| PD | Predicate disambiguation | batch_69adb847e9d881909dad2ffd0f3b6c15 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:25 p.m.