Triple

T32432475
Position Surface form Disambiguated ID Type / Status
Subject Exeter College Chapel E828763 entity
Predicate usedBy P260 FINISHED
Object fellows of Exeter College, Oxford
The fellows of Exeter College, Oxford are senior academic members of the college responsible for its teaching, research, and governance.
 E2006530 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: fellows of Exeter College, Oxford | Statement: [Exeter College Chapel, usedBy, fellows of Exeter College, Oxford]
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: fellows of Exeter College, Oxford
Triple: [Exeter College Chapel, usedBy, fellows of Exeter College, Oxford]
Generated description
The fellows of Exeter College, Oxford are senior academic members of the college responsible for its teaching, research, and governance.

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_69f3491bf298819097b610f772d54a6d completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6c2af5014819083835a701e683f4f completed May 3, 2026, 3:36 a.m.
NED1 Entity disambiguation (via context triple) batch_6a344f2f89f08190836855e106878652 completed June 18, 2026, 8:03 p.m.
NEDg Description generation batch_6a345176fb888190b58b7d32f631a58a completed June 18, 2026, 8:13 p.m.
NED2 Entity disambiguation (via description) batch_6a345ec17aec8190abe60c7682d1551e completed June 18, 2026, 9:10 p.m.
Created at: May 1, 2026, 12:55 a.m.