Triple
T10170563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Type 96 armored personnel carrier |
E235318
|
entity |
| Predicate | troopAccess |
P92211
|
FINISHED |
| Object | rear door |
—
|
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: rear door | Statement: [Type 96 armored personnel carrier, troopAccess, rear door]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: troopAccess Context triple: [Type 96 armored personnel carrier, troopAccess, rear door]
-
A.
crewAccess
Indicates that one entity has permission or authorization to access or enter an area, resource, or function reserved for crew members.
-
B.
peakTroopDeployment
Indicates the maximum number of troops that were deployed at any single point during a specified conflict or operation.
-
C.
typeOfTroops
Indicates the specific category or kind of military forces involved in or associated with an entity or event.
-
D.
battleGroup
Indicates that multiple military units or forces are organized together as a single coordinated combat formation.
-
E.
squadRestrictionForInvitedTeams
Indicates a constraint or rule that applies to the squad composition or size specifically for teams that have been invited.
- 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_69ca84ceafd0819085828600e11bed6b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdec9d36608190be78665cc3410cf2 |
completed | April 2, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69cd4ba9956c8190a3e15d091e33149d |
completed | April 1, 2026, 4:45 p.m. |
| PDg | Predicate description generation | batch_69cd4fed19d481909d2c7ff1114664b6 |
completed | April 1, 2026, 5:03 p.m. |
Created at: March 30, 2026, 9:10 p.m.