Triple
T5398013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bollingen Prize for Poetry |
E120703
|
entity |
| Predicate | juryComposedOf |
P20930
|
FINISHED |
| Object | poets |
—
|
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: poets | Statement: [Bollingen Prize for Poetry, juryComposedOf, poets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: juryComposedOf Context triple: [Bollingen Prize for Poetry, juryComposedOf, poets]
-
A.
juryComposition
chosen
Indicates the relationship specifying how a jury is constituted, including the number, type, or characteristics of its members.
-
B.
juryProvidedBy
Indicates that a particular jury is supplied, appointed, or made available by a specified source or authority.
-
C.
juryRole
Indicates that an entity serves in the capacity or function of a juror within a judicial or decision-making process.
-
D.
hasJurors
Indicates that one entity serves as or includes jurors in relation to another entity, typically in the context of a legal case or proceeding.
-
E.
hasNumberOfJurors
Indicates the relationship specifying how many jurors are associated with a given legal case, trial, or proceeding.
- 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_69bd4637b92c8190b815b6443ae4b323 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd8932b8bc8190bd31e11b167a7212 |
completed | March 20, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_69bd84660ea08190a641084814fcf94d |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:04 p.m.