Triple
T26074828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFET |
E657652
|
entity |
| Predicate | subcommitteeDROIStandsFor |
P70501
|
FINISHED |
| Object | Subcommittee on Human Rights |
—
|
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: Subcommittee on Human Rights | Statement: [AFET, subcommitteeDROIStandsFor, Subcommittee on Human Rights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subcommitteeDROIStandsFor Context triple: [AFET, subcommitteeDROIStandsFor, Subcommittee on Human Rights]
-
A.
isStandingCommitteeOf
Indicates that a committee is a permanent (standing) body formally established as part of, and operating under, a specific parent organization or legislative body.
-
B.
typeOfAppropriationsSubcommittee
Indicates that one entity is a specific type or category of an appropriations subcommittee in relation to another entity.
-
C.
hadSubcommittee
chosen
Indicates that an entity (typically an organization or committee) possessed or was associated with a subordinate committee or subcommittee.
-
D.
hasNumberOfSubcommittees
Indicates the relationship that specifies how many subcommittees are associated with a given entity.
-
E.
subDisciplineOf
Indicates that one discipline is a more specialized or narrower field within another, broader discipline.
- 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_69ee5bbe539081909efc7f9dd7c1b53c |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f606cec7f88190ac14980975171b6c |
completed | May 2, 2026, 2:14 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 7:33 p.m.