Triple
T18279705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M561 tractor unit |
E437831
|
entity |
| Predicate | couplingMethod |
P79973
|
FINISHED |
| Object | articulated joint with cargo body |
—
|
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: articulated joint with cargo body | Statement: [M561 tractor unit, couplingMethod, articulated joint with cargo body]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: couplingMethod Context triple: [M561 tractor unit, couplingMethod, articulated joint with cargo body]
-
A.
couplingCapability
Indicates the ability or suitability of one entity to connect, link, or interface with another in a functional or compatible manner.
-
B.
hasCoupling
Indicates that two entities are linked or joined together in a way that allows them to interact, transfer, or coordinate motion, energy, or information.
-
C.
hasCouplingConstant
Indicates that one entity is associated with a specific coupling constant value that quantifies the strength of an interaction or relationship.
-
D.
bindingMethod
chosen
Indicates the technique or process by which two or more entities are joined, attached, or held together.
-
E.
hasCouplers
Indicates that one entity is equipped with or possesses couplers that enable it to connect or link to 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50054d1dc8190b31d02f617256e9d |
completed | April 19, 2026, 4:18 p.m. |
| PD | Predicate disambiguation | batch_69e44fd81c788190b08c6be3b07a08c5 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:34 a.m.