Triple
T18474677
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Israel Horovitz |
E451397
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Matthew Horovitz
Matthew Horovitz is the son of the late American playwright and screenwriter Israel Horovitz.
|
E1326652
|
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: Matthew Horovitz | Statement: [Israel Horovitz, hasChild, Matthew Horovitz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matthew Horovitz Context triple: [Israel Horovitz, hasChild, Matthew Horovitz]
-
A.
Ari Schlossberg
Ari Schlossberg is an American screenwriter best known for writing the psychological horror film "Hide and Seek" (2005).
-
B.
Josh Weinstock
Josh Weinstock is a film and television producer known for his work on projects such as the drama "Nightingale."
-
C.
Andy Horwitz
Andy Horwitz is a film producer best known for his work on major action and thriller projects in Hollywood.
-
D.
Jonathan Lavine
Jonathan Lavine is an American investor and philanthropist best known as a senior executive and co-managing partner at the private investment firm Bain Capital.
-
E.
Jake Adelstein
Jake Adelstein is an American journalist and author best known for his memoir "Tokyo Vice," which chronicles his experiences reporting on crime and the yakuza for a major Japanese newspaper.
- 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: Matthew Horovitz Triple: [Israel Horovitz, hasChild, Matthew Horovitz]
Generated description
Matthew Horovitz is the son of the late American playwright and screenwriter Israel Horovitz.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Matthew Horovitz Target entity description: Matthew Horovitz is the son of the late American playwright and screenwriter Israel Horovitz.
-
A.
Ari Schlossberg
Ari Schlossberg is an American screenwriter best known for writing the psychological horror film "Hide and Seek" (2005).
-
B.
Josh Weinstock
Josh Weinstock is a film and television producer known for his work on projects such as the drama "Nightingale."
-
C.
Andy Horwitz
Andy Horwitz is a film producer best known for his work on major action and thriller projects in Hollywood.
-
D.
Jonathan Lavine
Jonathan Lavine is an American investor and philanthropist best known as a senior executive and co-managing partner at the private investment firm Bain Capital.
-
E.
Jake Adelstein
Jake Adelstein is an American journalist and author best known for his memoir "Tokyo Vice," which chronicles his experiences reporting on crime and the yakuza for a major Japanese newspaper.
- 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_69d8d38465a0819099b9b42d2a662ac1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53062387481909d4503fc963f9913 |
completed | April 19, 2026, 7:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a043f2ae2888190ae12fee12cf419ff |
completed | May 13, 2026, 9:06 a.m. |
| NEDg | Description generation | batch_6a043fd646b88190b0d232e740ae22ba |
completed | May 13, 2026, 9:09 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a04403951608190bc24c914175f18bc |
completed | May 13, 2026, 9:11 a.m. |
Created at: April 10, 2026, 11:34 a.m.