Triple
T25236909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M3 Bradley Cavalry Fighting Vehicle |
E632362
|
entity |
| Predicate | sharesChassisWith |
P174320
|
FINISHED |
| Object | M2 Bradley Infantry Fighting Vehicle |
—
|
NE NERFINISHED |
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: M2 Bradley Infantry Fighting Vehicle | Statement: [M3 Bradley Cavalry Fighting Vehicle, sharesChassisWith, M2 Bradley Infantry Fighting Vehicle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesChassisWith Context triple: [M3 Bradley Cavalry Fighting Vehicle, sharesChassisWith, M2 Bradley Infantry Fighting Vehicle]
-
A.
sharesTrunkWith
Indicates that two entities have a common trunk or main stem from which they both extend or branch.
-
B.
sharesMantleWith
Indicates that two entities occupy or are associated with the same mantle, layer, or mantle-like structure.
-
C.
wheelbaseSharedWith
Indicates that two vehicles have the same wheelbase dimensions or share a common wheelbase platform.
-
D.
sharesTrunkLineWith
Indicates that two entities are connected to or use the same primary communication or utility trunk line.
-
E.
chassisIntegrationWith
Indicates a relationship where one component or system is structurally or functionally integrated with a chassis as part of its overall assembly or design.
- 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_69e75a8ec5f88190b9eba06ae42b413a |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f6c20f209081909fb9ac8f95069f04 |
completed | May 3, 2026, 3:33 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2415fc81908c23c311aebce66f |
completed | May 3, 2026, 3:12 a.m. |
| PDg | Predicate description generation | batch_69f6c125695c81909704c67bef4ce5b2 |
completed | May 3, 2026, 3:29 a.m. |
Created at: April 21, 2026, 1:07 p.m.