Triple
T5531709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom & Viv |
E145063
|
entity |
| Predicate | mainSubject |
P3
|
FINISHED |
| Object | Vivienne Haigh-Wood |
E241494
|
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: Vivienne Haigh-Wood | Statement: [Tom & Viv, mainSubject, Vivienne Haigh-Wood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vivienne Haigh-Wood Context triple: [Tom & Viv, mainSubject, Vivienne Haigh-Wood]
-
A.
Vivienne Haigh-Wood
chosen
Vivienne Haigh-Wood was an English governess and writer best known as the first wife of poet T. S. Eliot and for her troubled marriage that significantly influenced his life and work.
-
B.
Vivienne Faull
Vivienne Faull is a senior Church of England bishop who has held prominent leadership roles, including serving as the diocesan bishop in Bristol.
-
C.
Anne Bracegirdle
Anne Bracegirdle was a celebrated late 17th-century English stage actress renowned for her virtuous public image and prominent roles in Restoration comedy.
-
D.
Clarissa Luard
Clarissa Luard was a British literary editor and arts administrator known for her work supporting contemporary writers and for her marriage to novelist Salman Rushdie.
-
E.
Bronwen Maddox
Bronwen Maddox is a British journalist and policy analyst who has held prominent leadership roles in UK public policy and media organizations.
- 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_69c008f9955881909bfa8348b56b4739 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f9d17ec8190b93b12931a4c1b33 |
completed | March 22, 2026, 4:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07d65dafc819083b60cbff2031819 |
completed | March 22, 2026, 11:38 p.m. |
Created at: March 22, 2026, 3:34 p.m.