Triple
T16333345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beatrice Straight |
E396610
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object | Whitney family |
E360589
|
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: Whitney family | Statement: [Beatrice Straight, memberOf, Whitney family]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Whitney family Context triple: [Beatrice Straight, memberOf, Whitney family]
-
A.
Whitney family
chosen
The Whitney family is a prominent American dynasty known for its substantial wealth, influence in business and finance, and patronage of the arts and philanthropy.
-
B.
Singer family
The Singer family is a prominent Jewish rabbinic and scholarly lineage known for its religious leadership and communal influence.
-
C.
Presley family
The Presley family is the famous American show-business dynasty centered around rock and roll icon Elvis Presley and his descendants.
-
D.
Fenty family
The Fenty family is the Barbadian family of global music and fashion icon Rihanna, around which her personal and business brand "Fenty" is built.
-
E.
Kelly family
The Kelly family is a prominent Irish-American crime family historically involved in organized criminal activities.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2c4e1da1081909bec6e77e6109dce |
completed | April 17, 2026, 11:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0026173dc081909e00f6647d1f68b3 |
completed | May 10, 2026, 6:30 a.m. |
Created at: April 10, 2026, 5:07 a.m.