Triple
T3826644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Ward as John Anglin |
E88705
|
entity |
| Predicate | escapePlanInvolvement |
P51071
|
FINISHED |
| Object | central |
—
|
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: central | Statement: [Fred Ward as John Anglin, escapePlanInvolvement, central]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: escapePlanInvolvement Context triple: [Fred Ward as John Anglin, escapePlanInvolvement, central]
-
A.
helpedEscape
Indicates that one entity assisted another in getting away from confinement, danger, or pursuit.
-
B.
fortInvolved
Indicates that a fort is involved or participates in a particular event, action, or relationship between entities.
-
C.
involvesIntendedVictim
Indicates that an action, event, or plan is directed toward and meant to affect a specific intended victim.
-
D.
hasPeopleInvolved
chosen
Indicates that certain people participate in, are associated with, or are otherwise involved in the referenced entity or event.
-
E.
escapeBehavior
Indicates a relationship where an entity actively attempts to avoid, flee from, or get away from another entity, situation, or constraint.
- 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_69aed9538cf881909d9ce8ca4ac7c18c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeb8459f881908a2c91bb07e381ef |
completed | March 9, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69aee74c2e04819094b94b3c0bac1806 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:17 p.m.