Triple
T28048515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Captain Elisabeth Campbell |
E708752
|
entity |
| Predicate | deathIsInvestigatedBy |
P97119
|
FINISHED |
| Object | Warrant Officer Paul Brenner |
—
|
NE NERFINISHED |
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: Warrant Officer Paul Brenner | Statement: [Captain Elisabeth Campbell, deathIsInvestigatedBy, Warrant Officer Paul Brenner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deathIsInvestigatedBy Context triple: [Captain Elisabeth Campbell, deathIsInvestigatedBy, Warrant Officer Paul Brenner]
-
A.
investigatesDeathOf
Indicates that one entity conducts an inquiry or investigation into the circumstances or cause of another entity’s death.
-
B.
hasCauseOfDeathInvestigation
chosen
Indicates that an entity is the subject of an official investigation into the circumstances or cause of its death.
-
C.
discoveredAsDeadBy
Indicates that one entity was found to be dead by another entity, who discovered their deceased state.
-
D.
hasMannerOfDeath
Indicates the specific way or circumstances in which an entity died, such as natural causes, accident, homicide, or suicide.
-
E.
deathIsWitnessedBy
Indicates that the occurrence of a death is directly observed or witnessed by another entity.
- 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_69ef9b6df9f48190bbb971d02cbe1b65 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f65a6c900881908f18b61273d7bf8d |
completed | May 2, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69f659ce58408190ba9e007b4810d4d0 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 27, 2026, 8:31 p.m.