Triple
T13762270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Mills |
E330641
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Mary Hayley Bell |
E497922
|
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: Mary Hayley Bell | Statement: [John Mills, spouse, Mary Hayley Bell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Hayley Bell Context triple: [John Mills, spouse, Mary Hayley Bell]
-
A.
Mary Hayley Bell
chosen
Mary Hayley Bell was a British novelist, playwright, and screenwriter best known for her novel "Whistle Down the Wind," which was adapted into a successful film and stage musical.
-
B.
Jane Bell
Jane Bell is known as the wife of Henry Bell, a figure associated with early steamship development.
-
C.
Mary Ryall
Mary Ryall is the daughter of mathematician and educationalist Mary Everest Boole.
-
D.
Mary Ellis
Mary Ellis was a British actress known for her work on stage and screen in the early to mid-20th century.
-
E.
Elizabeth Berrington
Elizabeth Berrington is a British actress known for her work in television, film, and theatre, including prominent roles in series such as The Syndicate.
- 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_69d81c573f288190aa2403d484fa3d49 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02250f4881908d5193b3d5d25844 |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7a8606dbc8190b0f7c38583986141 |
completed | May 3, 2026, 7:56 p.m. |
Created at: April 9, 2026, 10:10 p.m.