Triple
T6672909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J. David Sapir |
E151774
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object | William Sapir |
E614916
|
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: William Sapir | Statement: [J. David Sapir, sibling, William Sapir]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Sapir Context triple: [J. David Sapir, sibling, William Sapir]
-
A.
Edward Sapir
Edward Sapir was a pioneering American anthropologist-linguist whose work on language, culture, and cognition helped lay the foundations of modern linguistics and linguistic anthropology.
-
B.
J. David Sapir
J. David Sapir is an American anthropologist and linguist known for his work on West African languages and cultures and for being the son of renowned linguist Edward Sapir.
-
C.
Leonard Bloomfield
Leonard Bloomfield was an influential American linguist whose work in the early 20th century helped establish structural linguistics as a rigorous, scientific discipline.
-
D.
Jean Sapir
chosen
Jean Sapir is a member of the Sapir family, known primarily as the sibling of anthropologist and linguist J. David Sapir.
-
E.
Morris Swadesh
Morris Swadesh was an American linguist best known for pioneering lexicostatistics and glottochronology, methods for studying language classification and historical relationships through core vocabulary comparison.
- 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_69c687f71fc081909dbd45d6377f6045 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6b0cb78b08190923685712cbba5d8 |
completed | March 27, 2026, 4:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c71290084081909f23126c63d2d2ab |
completed | March 27, 2026, 11:28 p.m. |
Created at: March 27, 2026, 2:03 p.m.