Triple
T27319295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antonin Besse |
E689441
|
entity |
| Predicate | hasGivenEndowmentTo |
P135475
|
FINISHED |
| Object | UWC Atlantic College |
—
|
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: UWC Atlantic College | Statement: [Antonin Besse, hasGivenEndowmentTo, UWC Atlantic College]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGivenEndowmentTo Context triple: [Antonin Besse, hasGivenEndowmentTo, UWC Atlantic College]
-
A.
hasEndowmentType
Indicates that an entity is associated with a particular category or type of endowment.
-
B.
isEndowedBy
Indicates that something receives its funding, resources, or support from a particular source.
-
C.
hasEndowmentBeneficiary
chosen
Indicates that an entity is designated to receive benefits or distributions from another entity’s endowment.
-
D.
hasOriginalEndowmentPurpose
Indicates that an entity’s original endowment is intended or designated to serve a specific purpose or function.
-
E.
endowment
Indicates that a resource, asset, or benefit is provided or allocated to an entity, typically as a lasting or dedicated funding source.
- 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_69ef355c53a08190a8a92e355a7ce115 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 11:32 a.m.