Triple
T11558601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oenomaus |
E274075
|
entity |
| Predicate | hasDivineHorse |
P55479
|
FINISHED |
| Object | divine horses from Ares |
—
|
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: divine horses from Ares | Statement: [Oenomaus, hasDivineHorse, divine horses from Ares]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDivineHorse Context triple: [Oenomaus, hasDivineHorse, divine horses from Ares]
-
A.
hasNotableHorse
chosen
Indicates that an entity is associated with a horse that is considered notable or distinguished in some recognized way.
-
B.
hasDivineModel
Indicates that something is patterned after, based on, or derived from a divine or sacred archetype or example.
-
C.
hasViewOnDivinity
Indicates that an entity holds a particular belief, opinion, or perspective regarding divinity or the nature of the divine.
-
D.
hasMythicalFigure
Indicates that one entity is associated with, features, or includes a particular mythical or legendary figure.
-
E.
usesHorseType
Indicates that one entity employs, relies on, or operates using a specific type or category of horse.
- 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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88a888e8481909386009b9603e4d3 |
completed | April 10, 2026, 5:28 a.m. |
| PD | Predicate disambiguation | batch_69d85dc3fc2c8190bed7e2111301a77c |
completed | April 10, 2026, 2:17 a.m. |
Created at: April 8, 2026, 9:37 p.m.