Triple
T20882421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yoel Herzog |
E514183
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object | Herzog family |
—
|
NE NERFINISHED |
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: Herzog family | Statement: [Yoel Herzog, memberOf, Herzog family]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herzog family Context triple: [Yoel Herzog, memberOf, Herzog family]
-
A.
Herzog family
chosen
The Herzog family is a prominent Israeli family known for its influential roles in politics, public service, and cultural life.
-
B.
Schocken family
The Schocken family was a prominent German-Jewish business dynasty best known for its influential department store chain and cultural patronage in early 20th-century Germany.
-
C.
Hecht family
The Hecht family is a prominent American retailing dynasty best known for establishing and expanding the Hecht’s department store chain.
-
D.
Friedheim family
The Friedheim family is a philanthropic family known for supporting the arts, including endowing prestigious music composition awards.
-
E.
Buchmann family
The Buchmann family is a benefactor family whose name is associated with the Buchmann Faculty of Law, indicating their significant philanthropic or historical contribution to that institution.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c67a33548190b0f5ba58b001d387 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:46 p.m.