Triple
T24251466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eliza Hutton |
E603536
|
entity |
| Predicate | hasRelationshipToEvent |
P85529
|
FINISHED |
| Object | partner of victim in The Crow on-set shooting |
—
|
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: partner of victim in The Crow on-set shooting | Statement: [Eliza Hutton, hasRelationshipToEvent, partner of victim in The Crow on-set shooting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRelationshipToEvent Context triple: [Eliza Hutton, hasRelationshipToEvent, partner of victim in The Crow on-set shooting]
-
A.
relationshipToEvent
chosen
Indicates the specific way an entity is connected or related to a particular event.
-
B.
isLinkedToEvent
Indicates that an entity has an association or connection with a specific event.
-
C.
relativeInvolvedInEvent
Indicates that a person’s relative participates in, is affected by, or is otherwise involved in a particular event.
-
D.
hasCoSanctionedEventWith
Indicates that two or more entities have jointly imposed or participated in the same sanction-related event or action.
-
E.
hasRankAtTimeOfEvent
Indicates that an entity holds a specific rank or status at the time a particular event occurs.
- 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_69e29540da0481909a38bdae315b7a02 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28b89eb8081909ccf37081add5cee |
completed | April 29, 2026, 10:51 p.m. |
| PD | Predicate disambiguation | batch_69f1c450aa508190bc9d372a5f6ee47a |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:05 a.m.