Triple
T34581790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USUNESCO |
E887925
|
entity |
| Predicate | representsInterestsAt |
P149048
|
FINISHED |
| Object | UNESCO |
—
|
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: UNESCO | Statement: [USUNESCO, representsInterestsAt, UNESCO]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representsInterestsAt Context triple: [USUNESCO, representsInterestsAt, UNESCO]
-
A.
partyRepresentsInterestsOf
chosen
Indicates that one party acts to advocate for, protect, or advance the interests, needs, or goals of another party.
-
B.
representsInterestOf
Indicates that one entity expresses, holds, or embodies an interest, concern, or stake in another entity or subject.
-
C.
areRepresentedAt
Indicates that one entity serves as a representative or delegate for another entity at a specific place, event, or context.
-
D.
representedFor
Indicates that one entity has acted or served as the official representative or proxy on behalf of another entity.
-
E.
isRepresentedOn
Indicates that something serves as a visual, symbolic, or formal depiction of something else on a particular medium or surface.
- 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_69f349d25cbc8190869998de5915886b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff246e0d4481908bcec718e1d4025b |
completed | May 9, 2026, 12:11 p.m. |
| PD | Predicate disambiguation | batch_69ff23cb70ac81909b776ace4597ae9c |
completed | May 9, 2026, 12:08 p.m. |
Created at: May 1, 2026, 2:03 a.m.