Triple
T19387838
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hayes |
E484980
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Pat Hayes
Pat Hayes is a British computer scientist and philosopher renowned for his influential work in artificial intelligence and knowledge representation.
|
E1374433
|
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: Pat Hayes | Statement: [Hayes, hasNotableBearer, Pat Hayes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pat Hayes Context triple: [Hayes, hasNotableBearer, Pat Hayes]
-
A.
Patrick J. Hayes
Patrick J. Hayes was an American cardinal of the Roman Catholic Church who served as Archbishop of New York in the early 20th century.
-
B.
Ian Horrocks
Ian Horrocks is a British computer scientist known for his influential work in description logics and the development of the OWL Web Ontology Language.
-
C.
Colin Allen
Colin Allen is an author known for his work on the book "Medicine Jar."
-
D.
David Herman
David Herman is an American actor and comedian best known as an original cast member of MADtv and for his voice work on the animated series King of the Hill.
-
E.
Peter Giles
Peter Giles was a close friend and correspondent of Thomas More, featured as a character in More’s "Utopia" and known for his role in humanist intellectual circles of the early 16th century.
- 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: Pat Hayes Triple: [Hayes, hasNotableBearer, Pat Hayes]
Generated description
Pat Hayes is a British computer scientist and philosopher renowned for his influential work in artificial intelligence and knowledge representation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Pat Hayes Target entity description: Pat Hayes is a British computer scientist and philosopher renowned for his influential work in artificial intelligence and knowledge representation.
-
A.
Patrick J. Hayes
Patrick J. Hayes was an American cardinal of the Roman Catholic Church who served as Archbishop of New York in the early 20th century.
-
B.
Ian Horrocks
Ian Horrocks is a British computer scientist known for his influential work in description logics and the development of the OWL Web Ontology Language.
-
C.
Colin Allen
Colin Allen is an author known for his work on the book "Medicine Jar."
-
D.
David Herman
David Herman is an American actor and comedian best known as an original cast member of MADtv and for his voice work on the animated series King of the Hill.
-
E.
Peter Giles
Peter Giles was a close friend and correspondent of Thomas More, featured as a character in More’s "Utopia" and known for his role in humanist intellectual circles of the early 16th century.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b418f148190972b7b46038bc744 |
completed | April 20, 2026, 12:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a072b8503108190bfcd0ac7c94183f7 |
completed | May 15, 2026, 2:19 p.m. |
| NEDg | Description generation | batch_6a072dc9e9808190ab0e5b6dd35147ab |
completed | May 15, 2026, 2:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a072e3709e881909d70f130a77fc428 |
completed | May 15, 2026, 2:31 p.m. |
Created at: April 10, 2026, 1:36 p.m.