Triple
T12909395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret Salinger |
E308811
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Claire Douglas |
E337098
|
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: Claire Douglas | Statement: [Margaret Salinger, relative, Claire Douglas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Claire Douglas Context triple: [Margaret Salinger, relative, Claire Douglas]
-
A.
Claire Douglas
chosen
Claire Douglas was the second wife of reclusive American author J. D. Salinger and the mother of two of his children.
-
B.
Claire Dodd
Claire Dodd was an American film actress of the 1930s and 1940s, often cast as sophisticated or scheming society women in Hollywood productions.
-
C.
Claire Wright
Claire Wright is known as the wife of Tom Wright, a prominent British New Testament scholar and former Bishop of Durham.
-
D.
Claire Craig
Claire Craig is a British academic and former civil servant who serves as the Provost (head) of The Queen’s College, University of Oxford.
-
E.
Claire Brialey
Claire Brialey is a prominent British science fiction fan writer and fanzine editor recognized for her influential contributions to fandom and multiple Hugo Award wins.
- 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9719e584c81909be1ac1366effca0 |
completed | April 10, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcb63f006c8190997c0f3cdc6efd6c |
completed | May 7, 2026, 3:56 p.m. |
Created at: April 9, 2026, 5:41 p.m.