Triple

T11294969
Position Surface form Disambiguated ID Type / Status
Subject STPF E267426 entity
Predicate roleOfFellows P98363 FINISHED
Object advise on science and technology policy 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: advise on science and technology policy | Statement: [STPF, roleOfFellows, advise on science and technology policy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: roleOfFellows
Context triple: [STPF, roleOfFellows, advise on science and technology policy]
  • A. indicatesFellowshipIn
    Indicates that one entity holds a fellowship position, membership, or sponsored research role within another entity (such as an institution, organization, or program).
  • B. basisOfFellowship
    Indicates the foundational reason, condition, or shared element that forms the basis for a fellowship or partnership between entities.
  • C. campusRole
    Indicates the specific position, function, or capacity an individual holds within a campus or academic institution.
  • D. formsFellowshipOf
    Indicates that one entity creates or establishes a fellowship or alliance together with another entity or group of entities.
  • E. alumniRole
    Indicates that an entity holds or held a specific role, position, or capacity as an alumnus/alumna of another entity (such as an institution or program).
  • F. None of above. chosen

Provenance (4 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_69d6aac993a08190a6f36445ebaf9a43 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e98b149481909f432a6b9ef8bfbb completed April 9, 2026, 6:01 p.m.
PD Predicate disambiguation batch_69d787a6ca2c8190afdc24b61ccd3f8a completed April 9, 2026, 11:04 a.m.
PDg Predicate description generation batch_69d796d049e88190a9fd7508f477f541 completed April 9, 2026, 12:08 p.m.
Created at: April 8, 2026, 9:32 p.m.