Triple
T8730193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Hillary |
E207234
|
entity |
| Predicate | coAuthor |
P398
|
FINISHED |
| Object |
John Elder
John Elder is an author known for co-writing works with New Zealand mountaineer and adventurer Peter Hillary.
|
E753488
|
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: John Elder | Statement: [Peter Hillary, coAuthor, John Elder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Elder Context triple: [Peter Hillary, coAuthor, John Elder]
-
A.
John Alderman
John Alderman was a Native American allied with the English colonists who became historically known for killing the Wampanoag leader Metacomet (King Philip) during King Philip’s War.
-
B.
Edward Reeves
Edward Reeves was a teacher and mentor known for instructing Lionel Logue, the Australian speech therapist famous for treating King George VI.
-
C.
William Nolan
William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
-
D.
David Anspaugh
David Anspaugh is an American film and television director best known for directing the sports dramas "Hoosiers" and "Rudy."
-
E.
Jack Daugherty
Jack Daugherty was an American record producer best known for his work with the Carpenters, including producing their breakthrough hit "(They Long to Be) Close to You."
- 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: John Elder Triple: [Peter Hillary, coAuthor, John Elder]
Generated description
John Elder is an author known for co-writing works with New Zealand mountaineer and adventurer Peter Hillary.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Elder Target entity description: John Elder is an author known for co-writing works with New Zealand mountaineer and adventurer Peter Hillary.
-
A.
John Alderman
John Alderman was a Native American allied with the English colonists who became historically known for killing the Wampanoag leader Metacomet (King Philip) during King Philip’s War.
-
B.
Edward Reeves
Edward Reeves was a teacher and mentor known for instructing Lionel Logue, the Australian speech therapist famous for treating King George VI.
-
C.
William Nolan
William Nolan is an editor known for his work on editions of classic adventure literature, including "The Mark of Zorro."
-
D.
David Anspaugh
David Anspaugh is an American film and television director best known for directing the sports dramas "Hoosiers" and "Rudy."
-
E.
Jack Daugherty
Jack Daugherty was an American record producer best known for his work with the Carpenters, including producing their breakthrough hit "(They Long to Be) Close to You."
- 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_69ca8358e4008190898471a59b96c301 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d26d280819085e15d4917c2b9a5 |
completed | March 31, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf2923abc48190a5b6027c2e4f1db7 |
completed | April 3, 2026, 2:42 a.m. |
| NEDg | Description generation | batch_69cf2bd42e6081908e016303eeb2241f |
completed | April 3, 2026, 2:54 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cf2ce47b748190b883063dc3e5d16b |
completed | April 3, 2026, 2:58 a.m. |
Created at: March 30, 2026, 6:37 p.m.