Triple
T22962638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andrew Hamilton |
E570942
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Anne Brownlow |
—
|
NE NERFINISHED |
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: Anne Brownlow | Statement: [Andrew Hamilton, spouse, Anne Brownlow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anne Brownlow Context triple: [Andrew Hamilton, spouse, Anne Brownlow]
-
A.
Anne Brownlow
chosen
Anne Brownlow was a member of the Anglo-Irish Brownlow family, known primarily through her marriage to Andrew Hamilton.
-
B.
Elizabeth Lamb
Elizabeth Lamb is the central protagonist of the psychological thriller film "Trance," around whom the story’s mind-bending art heist and memory-manipulation plot revolves.
-
C.
Elizabeth Lamb
Elizabeth Lamb is the mother of Joe Lamb, a central character in the 2011 science fiction film "Super 8."
-
D.
Elizabeth Lamb
Elizabeth Lamb is the wife of Deputy Jackson Lamb, known primarily in relation to his public role.
-
E.
Letitia Cropley
Letitia Cropley is an eccentric parishioner in the British sitcom "The Vicar of Dibley," best known for her bizarre and unappetizing culinary creations.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b212a88190b5259caf51606084 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f181f594fc8190816418486b798198 |
completed | April 29, 2026, 3:58 a.m. |
Created at: April 17, 2026, 3:47 p.m.