Triple
T37337892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phil Esterhaus |
E926946
|
entity |
| Predicate | reasonForCharacterExit |
P15987
|
FINISHED |
| Object | death of actor Michael Conrad |
—
|
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: death of actor Michael Conrad | Statement: [Phil Esterhaus, reasonForCharacterExit, death of actor Michael Conrad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reasonForCharacterExit Context triple: [Phil Esterhaus, reasonForCharacterExit, death of actor Michael Conrad]
-
A.
reasonForLeaving
chosen
Indicates the cause, motivation, or circumstance that led an entity to depart or discontinue an association, position, or place.
-
B.
reasonForWalkout
Indicates the cause or motivation behind a walkout event.
-
C.
departureStory
Indicates a narrative or account describing how, why, and under what circumstances an entity left or departed from a place, role, or situation.
-
D.
dismissesCharacter
Indicates that one character rejects, disbelieves, or disregards another character, often minimizing their importance, ideas, or concerns.
-
E.
coveredReasonForLeave
Indicates that a specified reason for leave is included under and qualifies for coverage within a particular leave policy or program.
- 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_69f76eb4e8a881908bd40da28f36fc7e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe38be079c8190a240191ac0e73e3a |
completed | May 8, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69fe350344508190930de2218156ca02 |
completed | May 8, 2026, 7:09 p.m. |
Created at: May 3, 2026, 4:16 p.m.