Triple
T24033722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Multinational Force in Lebanon |
E595170
|
entity |
| Predicate | USComponent |
P70977
|
FINISHED |
| Object | U.S. Marine Corps units |
—
|
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: U.S. Marine Corps units | Statement: [Multinational Force in Lebanon, USComponent, U.S. Marine Corps units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: USComponent Context triple: [Multinational Force in Lebanon, USComponent, U.S. Marine Corps units]
-
A.
usedComponent
Indicates that one entity has employed or incorporated another entity as a component in its structure, function, or operation.
-
B.
isCoreComponentOf
Indicates that something is an essential, foundational part required for the structure, function, or identity of another entity.
-
C.
U.S.component
chosen
Indicates that something is a constituent part, subdivision, or member unit within the United States.
-
D.
otherComponentOf
Indicates that one entity is a different part or member of the same larger whole or system as another entity.
-
E.
componentCC
Indicates that one entity is a component or constituent part of another entity within a coordinated or composite construction.
- 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_69e288bf45f08190a1b6ed8cd0b9e86b |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d8d0ec8081908f98e78944bff040 |
completed | April 29, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:56 p.m.