Triple
T7974678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lisa Bonet |
E185413
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object |
Allen Bonet
Allen Bonet was the father of American actress Lisa Bonet and is primarily known to the public through this familial connection.
|
E703018
|
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: Allen Bonet | Statement: [Lisa Bonet, parent, Allen Bonet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Allen Bonet Context triple: [Lisa Bonet, parent, Allen Bonet]
-
A.
Guy Trosper
Guy Trosper was an American screenwriter known for his work on mid-20th-century Hollywood films, including several notable dramas and biographical movies.
-
B.
Rob Bourdon
Rob Bourdon is an American musician best known as the drummer and a founding member of the rock band Linkin Park.
-
C.
Andrew Sarlo
Andrew Sarlo is a music producer known for his work with indie and alternative artists such as Big Thief and Bon Iver.
-
D.
Steve Martino
Steve Martino is an American film director best known for his work on animated features such as "Horton Hears a Who!" and "The Peanuts Movie."
-
E.
Delmar Arnaud
Delmar Arnaud, better known as Daz Dillinger, is an American rapper and record producer famed for his work with Death Row Records and contributions to West Coast hip hop.
- 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: Allen Bonet Triple: [Lisa Bonet, parent, Allen Bonet]
Generated description
Allen Bonet was the father of American actress Lisa Bonet and is primarily known to the public through this familial connection.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Allen Bonet Target entity description: Allen Bonet was the father of American actress Lisa Bonet and is primarily known to the public through this familial connection.
-
A.
Guy Trosper
Guy Trosper was an American screenwriter known for his work on mid-20th-century Hollywood films, including several notable dramas and biographical movies.
-
B.
Rob Bourdon
Rob Bourdon is an American musician best known as the drummer and a founding member of the rock band Linkin Park.
-
C.
Andrew Sarlo
Andrew Sarlo is a music producer known for his work with indie and alternative artists such as Big Thief and Bon Iver.
-
D.
Steve Martino
Steve Martino is an American film director best known for his work on animated features such as "Horton Hears a Who!" and "The Peanuts Movie."
-
E.
Delmar Arnaud
Delmar Arnaud, better known as Daz Dillinger, is an American rapper and record producer famed for his work with Death Row Records and contributions to West Coast hip hop.
- 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_69ca829851908190b4e03829353ee7c3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3bf42a508190bb661fce34ec0151 |
completed | March 31, 2026, 3:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe0c39e248190a146c1f2fd815f26 |
completed | March 31, 2026, 2:57 p.m. |
| NEDg | Description generation | batch_69cbe43d29f8819080f7d729c4f28c75 |
completed | March 31, 2026, 3:11 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc32e2e1c48190b86218bff9af99f5 |
completed | March 31, 2026, 8:47 p.m. |
Created at: March 30, 2026, 5:14 p.m.