Triple
T15320352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isabel Colegate |
E366270
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object |
Colegate
Colegate is an English surname most notably associated with the novelist Isabel Colegate.
|
E1150470
|
NE FINISHED |
How this triple was built (4 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: Colegate | Statement: [Isabel Colegate, familyName, Colegate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Colegate Context triple: [Isabel Colegate, familyName, Colegate]
-
A.
College Hall
College Hall is the main dining hall of Corpus Christi College, University of Cambridge, where students and fellows gather for formal and informal meals.
-
B.
Berrick Hall
Berrick Hall is a historic Western-style residence in Yokohama’s Yamate district, known for its early 20th-century architecture and role in the city’s foreign settlement history.
-
C.
Heythrop
Heythrop is a small rural village in West Oxfordshire, England, known for its historic country estate and tranquil countryside setting.
-
D.
Harkness Hall
Harkness Hall is an academic building located on the University of Rochester’s River Campus, housing classrooms and faculty offices.
-
E.
Vanbrugh College
Vanbrugh College is one of the constituent residential and academic colleges of the University of York, known for its central campus location and active student community.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Colegate Triple: [Isabel Colegate, familyName, Colegate]
Generated description
Colegate is an English surname most notably associated with the novelist Isabel Colegate.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Colegate Target entity description: Colegate is an English surname most notably associated with the novelist Isabel Colegate.
-
A.
College Hall
College Hall is the main dining hall of Corpus Christi College, University of Cambridge, where students and fellows gather for formal and informal meals.
-
B.
Berrick Hall
Berrick Hall is a historic Western-style residence in Yokohama’s Yamate district, known for its early 20th-century architecture and role in the city’s foreign settlement history.
-
C.
Heythrop
Heythrop is a small rural village in West Oxfordshire, England, known for its historic country estate and tranquil countryside setting.
-
D.
Harkness Hall
Harkness Hall is an academic building located on the University of Rochester’s River Campus, housing classrooms and faculty offices.
-
E.
Vanbrugh College
Vanbrugh College is one of the constituent residential and academic colleges of the University of York, known for its central campus location and active student community.
- F. None of above. chosen
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_69d85a121520819093dcce999fdefe1a |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03dd460288190b5c41f0a0aeee949 |
completed | April 16, 2026, 1:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fef8a9085881909904152c32b0fed1 |
completed | May 9, 2026, 9:04 a.m. |
| NEDg | Description generation | batch_69fefc8251d08190bf8a764f83f89d7e |
completed | May 9, 2026, 9:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fefd6c2bf88190b17a03be7b3353e3 |
completed | May 9, 2026, 9:25 a.m. |
Created at: April 10, 2026, 3:16 a.m.