Triple

T25204490
Position Surface form Disambiguated ID Type / Status
Subject Bison E631211 entity
Predicate homeVenue P105 FINISHED
Object Graham Field at Holmes Stadium
Graham Field at Holmes Stadium is a college sports facility that serves as the primary home field for the Bucknell Bison athletic teams.
E1669142 NE 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: Graham Field at Holmes Stadium | Statement: [Bison, homeVenue, Graham Field at Holmes Stadium]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Graham Field at Holmes Stadium
Triple: [Bison, homeVenue, Graham Field at Holmes Stadium]
Generated description
Graham Field at Holmes Stadium is a college sports facility that serves as the primary home field for the Bucknell Bison athletic teams.

Provenance (5 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_69e75a8b86c4819089eda22c843b739f completed April 21, 2026, 11:07 a.m.
NER Named-entity recognition batch_69f474baf50c81909ef63b5ec7d42bfd completed May 1, 2026, 9:39 a.m.
NED1 Entity disambiguation (via context triple) batch_6a105d2e828481908a413f5da300e861 completed May 22, 2026, 1:42 p.m.
NEDg Description generation batch_6a105e53f9bc8190a4b0929a68d83b0a completed May 22, 2026, 1:47 p.m.
NED2 Entity disambiguation (via description) batch_6a105ed31dd481908a09f91fcb860641 completed May 22, 2026, 1:49 p.m.
Created at: April 21, 2026, 12:52 p.m.