Triple
T10794735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter A. Haas Sr. |
E254673
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Elise Stern |
E254673
|
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: Elise Stern | Statement: [Walter A. Haas Sr., spouse, Elise Stern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elise Stern Context triple: [Walter A. Haas Sr., spouse, Elise Stern]
-
A.
Elise Stern
chosen
Elise Stern was the wife of American businessman and former Levi Strauss & Co. president Walter A. Haas Sr., and a member of a prominent San Francisco Jewish philanthropic family.
-
B.
Elise Muller
Elise Muller is an actress best known for her role in the indie horror-comedy film "Baghead."
-
C.
Elise Pearlstein
Elise Pearlstein is an American film producer best known for her work on acclaimed documentaries, including the Oscar-nominated "Food, Inc."
-
D.
Elise Kraft
Elise Kraft is the central FBI agent protagonist in the 1998 political thriller film "The Siege," navigating the moral and legal tensions of counterterrorism in New York City.
-
E.
Elise Wassermann
Elise Wassermann is a brilliant but emotionally detached French detective in the Anglo-French crime drama series "The Tunnel."
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733321dd881909dcd4224dfa9822a |
completed | April 9, 2026, 5:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de564748ac8190beaaea44bb2d95ed |
completed | April 14, 2026, 2:59 p.m. |
Created at: April 8, 2026, 9:17 p.m.