Triple
T794139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Humvee |
E16979
|
entity |
| Predicate | usedAsPlatformFor |
P1292
|
FINISHED |
| Object | machine guns |
—
|
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: machine guns | Statement: [Humvee, usedAsPlatformFor, machine guns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsPlatformFor Context triple: [Humvee, usedAsPlatformFor, machine guns]
-
A.
consideredPlatform
Indicates that one entity is regarded or treated as a platform (e.g., a base, medium, or environment) for another entity or activity.
-
B.
platforms
chosen
Indicates that one entity provides or serves as a base, medium, or environment that supports the operation, distribution, or presentation of another entity.
-
C.
usedOn
Indicates that one entity is applied to, operated on, or otherwise utilized in relation to another entity.
-
D.
alsoUsedBy
Indicates that something is additionally utilized or employed by another entity, beyond any primary or previously mentioned user.
-
E.
hasPrimaryPlatform
Indicates that one entity is designated as the main or principal platform associated with another entity.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a79b976c819085cd381bbd597ca5 |
completed | March 1, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69a4a510f61881909175d6d8719246cd |
completed | March 1, 2026, 8:44 p.m. |
Created at: March 1, 2026, 7:38 p.m.