Triple
T23127892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Γραῖαι |
E577083
|
entity |
| Predicate | usedByHero |
P31799
|
FINISHED |
| Object | Perseus seizes their eye to force information |
—
|
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: Perseus seizes their eye to force information | Statement: [Γραῖαι, usedByHero, Perseus seizes their eye to force information]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedByHero Context triple: [Γραῖαι, usedByHero, Perseus seizes their eye to force information]
-
A.
usedByCharacter
chosen
Indicates that something (such as an item, ability, or resource) is utilized or employed by a particular character.
-
B.
baseHero
Indicates that one entity serves as the primary or foundational hero associated with another entity.
-
C.
hasHeroPower
Indicates that one entity possesses or is endowed with a special ability or power characteristic of a hero in relation to another entity.
-
D.
usedAgainst
Indicates that one entity is employed, applied, or deployed in opposition to, or for the purpose of affecting, another entity.
-
E.
usedByMission
Indicates that something (such as a resource, tool, or method) is utilized or employed in the execution of a particular mission.
- 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_69e245f7b0e481909c473ff4e6a54e2c |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e55aa38819092816ffc52e20dbe |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f83b108190aaaa1db6221fc163 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.