Triple
T4296892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John McCain |
E99734
|
entity |
| Predicate | POWStatus |
P55309
|
FINISHED |
| Object | prisoner of war in North Vietnam |
—
|
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: prisoner of war in North Vietnam | Statement: [John McCain, POWStatus, prisoner of war in North Vietnam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: POWStatus Context triple: [John McCain, POWStatus, prisoner of war in North Vietnam]
-
A.
peakStatus
Indicates the condition or phase of something at its highest or most intense point in its progression or lifecycle.
-
B.
positionOnStatePower
Indicates a stance or viewpoint an entity holds regarding the nature, scope, or use of state power.
-
C.
powerStatus
Indicates whether an entity is currently powered on, off, or in another defined power state.
-
D.
playerStatus
Indicates the current state or condition of a player within a game or system, such as their activity, health, or participation status.
-
E.
opposingForcesStatus
Indicates the current state or condition of two or more forces that are in conflict or opposition to each other.
- F. None of above. chosen
Provenance (4 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_69b3455175088190aa79c6e03b86647e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3509aebd48190af38f2e37f07869a |
completed | March 12, 2026, 11:47 p.m. |
| PD | Predicate disambiguation | batch_69b347fe55a88190b77bab0c0f38e1aa |
completed | March 12, 2026, 11:10 p.m. |
| PDg | Predicate description generation | batch_69b34e0606488190baadf469a1afc3c2 |
completed | March 12, 2026, 11:36 p.m. |
Created at: March 12, 2026, 11:08 p.m.