Triple
T7701366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Amir |
E174503
|
entity |
| Predicate | hasSpouse |
P13
|
FINISHED |
| Object | Herta Amir |
E174502
|
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: Herta Amir | Statement: [Paul Amir, hasSpouse, Herta Amir]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herta Amir Context triple: [Paul Amir, hasSpouse, Herta Amir]
-
A.
Herta Amir
chosen
Herta Amir is a benefactor whose philanthropy is commemorated through the naming of the Herta and Paul Amir Building.
-
B.
Herta Haas
Herta Haas was a Slovenian communist and partisan who became known as the second wife of Yugoslav leader Josip Broz Tito.
-
C.
Leila Gerstein
Leila Gerstein is an American television writer and producer best known for creating the comedy-drama series "Hart of Dixie."
-
D.
Sarah Herzog
Sarah Herzog was a prominent Jewish community leader and rebbetzin, known especially as the wife of Israel’s second Chief Rabbi, Yitzhak HaLevi Herzog, and matriarch of the influential Herzog family.
-
E.
Zohra Lampert
Zohra Lampert is an American actress known for her nuanced performances in film, television, and theater, including acclaimed roles in 1960s cinema and later cult horror.
- 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_69c6995a72cc8190998e56daa6f8e453 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c70288d02c819093d6f0e47707d0a3 |
completed | March 27, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8dea25d2081908ebbf2bb5f94b7d6 |
completed | March 29, 2026, 8:11 a.m. |
Created at: March 27, 2026, 4:03 p.m.