Triple
T14238872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jo Grant |
E352955
|
entity |
| Predicate | departureReason |
P24494
|
FINISHED |
| Object | left UNIT to marry Cliff Jones |
—
|
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: left UNIT to marry Cliff Jones | Statement: [Jo Grant, departureReason, left UNIT to marry Cliff Jones]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: departureReason Context triple: [Jo Grant, departureReason, left UNIT to marry Cliff Jones]
-
A.
reasonForDismissal
Indicates the cause or justification for which an entity (such as a person, case, or item) was dismissed, terminated, or removed.
-
B.
coveredReasonForLeave
Indicates that a specified reason for leave is included under and qualifies for coverage within a particular leave policy or program.
-
C.
statedReason
chosen
Indicates that one entity expresses or provides another entity as the explanation, justification, or motive for an action, event, or claim.
-
D.
abandonedReason
Indicates the reason or cause for which something was abandoned, discontinued, or given up.
-
E.
expulsionReason
Indicates the cause or justification for which an entity was expelled from a group, place, or institution.
- 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_69d8278adc7c8190a9218d69bce3c4e6 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de62432fb48190b153805b85c4f2d2 |
completed | April 14, 2026, 3:50 p.m. |
| PD | Predicate disambiguation | batch_69de05bf069c8190b69f00f00f5eb126 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 1:08 a.m.