Triple
T7769278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Segal |
E179027
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Sonia Segal |
E688305
|
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: Sonia Segal | Statement: [George Segal, spouse, Sonia Segal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonia Segal Context triple: [George Segal, spouse, Sonia Segal]
-
A.
Vivienne Segal
Vivienne Segal was an American actress and singer best known as a leading lady of Broadway musicals in the early to mid-20th century.
-
B.
Ronit Matalon
Ronit Matalon was an Israeli author known for her innovative Hebrew prose that explored themes of identity, family, and Mizrahi experience in contemporary Israeli society.
-
C.
Marianne Segal
chosen
Marianne Segal is best known as the wife of late American actor George Segal, with whom she shared a long-term marriage later in his life.
-
D.
Ilene Chaiken
Ilene Chaiken is an American television writer and producer best known as the creator of "The L Word" and a key creative force behind several high-profile drama series.
-
E.
Sandra Levy
Sandra Levy is an Australian film producer known for her work on acclaimed features such as the 1987 drama "High Tide."
- 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_69c69f30602c819082ab52cd4af5c592 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c704376dc08190890f5ebb9f259cfd |
completed | March 27, 2026, 10:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8deb127048190a89c08b7778df8a4 |
completed | March 29, 2026, 8:11 a.m. |
Created at: March 27, 2026, 4:11 p.m.