Triple
T10296286
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ted Hughes |
E241496
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Carol Orchard |
E241496
|
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: Carol Orchard | Statement: [Ted Hughes, spouse, Carol Orchard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carol Orchard Context triple: [Ted Hughes, spouse, Carol Orchard]
-
A.
Carol Orchard
chosen
Carol Orchard is an English nurse best known as the second wife of poet Ted Hughes, whom she married in 1970.
-
B.
Anne Heywood
Anne Heywood is a British actress known for her film and television roles from the 1950s through the 1970s, often portraying strong, complex female characters.
-
C.
Alice Hanthorn
Alice Hanthorn was the wife of American businessman and government official Lewis L. Strauss, associated with his early life and career before his prominence in nuclear policy.
-
D.
Carol Vanstone
Carol Vanstone is a high-powered, no-nonsense CEO and the sister of a laid-back branch manager in the comedy film "Office Christmas Party."
-
E.
Patricia Bloomfield
Patricia Bloomfield is known as the wife of renowned Dutch conductor Bernard Haitink.
- 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2ea9b3c8190b11518b259d5825c |
completed | April 7, 2026, 9:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71d23f49081909aea149c6b219354 |
completed | April 9, 2026, 3:29 a.m. |
Created at: April 6, 2026, 11:43 a.m.