Triple
T15696434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brad Whitaker |
E380471
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Sara Whitaker |
E1015753
|
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: Sara Whitaker | Statement: [Brad Whitaker, spouse, Sara Whitaker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sara Whitaker Context triple: [Brad Whitaker, spouse, Sara Whitaker]
-
A.
Sara Whitaker
chosen
Sara Whitaker is known as the spouse of Brad Whitaker.
-
B.
Sara Whitaker
Sara Whitaker is a supporting character in the comedy film "Daddy's Home 2," involved in the blended-family holiday chaos central to the movie's plot.
-
C.
Sara White
Sara White was the wife of American novelist and journalist Theodore Dreiser.
-
D.
Sara Potts
Sara Potts is known as the sister of American actress and television personality Olivia Munn.
-
E.
Sara Stewart
Sara Stewart is a Scottish-born actress known for her work in British television, film, and theatre, including roles in series like "Doctor Foster" and "Sugar Rush."
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f6c3328819081325b702ca92862 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00cfb725d48190bdca0a85ca7f440c |
completed | May 10, 2026, 6:34 p.m. |
Created at: April 10, 2026, 4:44 a.m.