Triple
T22150725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ostrowski Prize |
E547404
|
entity |
| Predicate | eligibleField |
P98750
|
FINISHED |
| Object | number theory |
—
|
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: number theory | Statement: [Ostrowski Prize, eligibleField, number theory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eligibleField Context triple: [Ostrowski Prize, eligibleField, number theory]
-
A.
eligibleFrom
Indicates that a subject becomes or is considered eligible starting from a specified point in time or condition.
-
B.
eligibleIn
chosen
Indicates that an entity meets the necessary conditions or criteria to qualify for participation, use, or consideration within a specified context, domain, or scope.
-
C.
eligibleOn
Indicates the date or condition from which something qualifies to begin or be considered valid or applicable.
-
D.
holderField
Indicates that a specified field or attribute belongs to, is maintained by, or is associated with a particular holder entity.
-
E.
eligibleWorkField
Indicates that a particular field of work is considered suitable or permitted for a given entity (such as a person, role, or position).
- 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_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129f37dac8190a7cecb12f4271515 |
completed | April 28, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69e71b384e008190b723c9a0f1089d66 |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:33 p.m.