Triple
T8140418
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arthur Middleton |
E190080
|
entity |
| Predicate | wasTakenPrisonerOfWar |
P45720
|
FINISHED |
| Object | 1780 |
—
|
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: 1780 | Statement: [Arthur Middleton, wasTakenPrisonerOfWar, 1780]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasTakenPrisonerOfWar Context triple: [Arthur Middleton, wasTakenPrisonerOfWar, 1780]
-
A.
UnionPrisonersTaken
Indicates that Union forces captured and held individuals as prisoners.
-
B.
capturedInWar
chosen
Indicates that one entity was taken prisoner or seized by another entity as a result of armed conflict or wartime actions.
-
C.
prisonersOfWar
Indicates a relationship where certain individuals are held in custody by an enemy during an armed conflict as prisoners of war.
-
D.
prisonerOf
Indicates that one entity is held in custody or confinement by another entity, typically under legal or authoritative control.
-
E.
captivesTaken
Indicates that one entity has taken another entity or group into captivity, holding them against their will.
- 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_69ca82bd9900819099477cdc2eb4244f |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4404e5308190a323485701f09d86 |
completed | March 31, 2026, 3:48 a.m. |
| PD | Predicate disambiguation | batch_69cb369c0d0481908762c488d7f77e74 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:36 p.m.