Triple
T4724700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Delsohn |
E104853
|
entity |
| Predicate | coAuthorWith |
P398
|
FINISHED |
| Object |
Mark Heisler
Mark Heisler is an American sports journalist and author best known for his long-time NBA coverage and basketball writing, including work for the Los Angeles Times.
|
E525456
|
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: Mark Heisler | Statement: [Steve Delsohn, coAuthorWith, Mark Heisler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Heisler Context triple: [Steve Delsohn, coAuthorWith, Mark Heisler]
-
A.
Matthew Weisman
Matthew Weisman is a screenwriter best known for co-writing the 1985 action film "Commando" starring Arnold Schwarzenegger.
-
B.
John Eisendrath
John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
-
C.
Eric Wetzels
Eric Wetzels is a Dutch politician who serves as the chairperson of the People's Party for Freedom and Democracy (VVD).
-
D.
Michael Leeson
Michael Leeson was an American television writer and producer best known for co-creating the groundbreaking sitcom "The Cosby Show."
-
E.
Jeremy Adelman
Jeremy Adelman is a composer best known for creating music for television, including the series "Hart of Dixie."
- 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: Mark Heisler Triple: [Steve Delsohn, coAuthorWith, Mark Heisler]
Generated description
Mark Heisler is an American sports journalist and author best known for his long-time NBA coverage and basketball writing, including work for the Los Angeles Times.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mark Heisler Target entity description: Mark Heisler is an American sports journalist and author best known for his long-time NBA coverage and basketball writing, including work for the Los Angeles Times.
-
A.
Matthew Weisman
Matthew Weisman is a screenwriter best known for co-writing the 1985 action film "Commando" starring Arnold Schwarzenegger.
-
B.
John Eisendrath
John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
-
C.
Eric Wetzels
Eric Wetzels is a Dutch politician who serves as the chairperson of the People's Party for Freedom and Democracy (VVD).
-
D.
Michael Leeson
Michael Leeson was an American television writer and producer best known for co-creating the groundbreaking sitcom "The Cosby Show."
-
E.
Jeremy Adelman
Jeremy Adelman is a composer best known for creating music for television, including the series "Hart of Dixie."
- 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_69bd43ed84648190ae0b7ee8e8d00482 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64456a6c8190b658216b62ef82cf |
completed | March 20, 2026, 3:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf8bbef34c8190ae4b22a94e1cf91a |
completed | March 22, 2026, 6:27 a.m. |
| NEDg | Description generation | batch_69bf8daadc44819098c353390d06f540 |
completed | March 22, 2026, 6:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf8e5765188190952e26e42b288531 |
completed | March 22, 2026, 6:38 a.m. |
Created at: March 20, 2026, 1:18 p.m.