Triple
T12932013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Weitz |
E309406
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | John Weitz |
E309407
|
NE FINISHED |
How this triple was built (2 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 Weitz | Statement: [Paul Weitz, relative, John Weitz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Weitz Context triple: [Paul Weitz, relative, John Weitz]
-
A.
John Weitz
chosen
John Weitz was a German-born American fashion designer and author known for his influential menswear designs and historical writings.
-
B.
Robert Weil
Robert Weil is a name shared by several notable individuals, including figures in fields such as winemaking, philanthropy, and academia.
-
C.
Robert M. Weitman
Robert M. Weitman was an American film producer active in mid-20th-century Hollywood, known for overseeing a range of studio features and genre films.
-
D.
Joseph Leiter
Joseph Leiter was an American businessman and investor from the prominent Leiter family, known for his involvement in late 19th-century grain speculation and Chicago enterprises.
-
E.
Michael J. Weithorn
Michael J. Weithorn is an American television writer and producer best known for creating and working on several sitcoms, including "Ned and Stacey" and "The King of Queens."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d7bdfa933c8190b5a27aa4a08a19b7 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97dc53060819090a126f15428e411 |
completed | April 10, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6b8d58a0c8190b96252f04fdf1256 |
completed | May 3, 2026, 2:54 a.m. |
Created at: April 9, 2026, 5:42 p.m.