Triple
T2240946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Frayn |
E49393
|
entity |
| Predicate | placeOfBirth |
P1
|
FINISHED |
| Object | Mill Hill |
E279231
|
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: Mill Hill | Statement: [Michael Frayn, placeOfBirth, Mill Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mill Hill Context triple: [Michael Frayn, placeOfBirth, Mill Hill]
-
A.
Mills Hill
Mills Hill is a railway station in Greater Manchester, England, serving the local communities of Middleton and Chadderton.
-
B.
Vernon Hill
Vernon Hill was a British sculptor and illustrator known for his expressive architectural and memorial works in the early 20th century.
-
C.
Stanmore
chosen
Stanmore is a suburban district in the London Borough of Harrow, England, known for its residential character and historical connections, including former Royal Air Force sites.
-
D.
Herne Hill
Herne Hill is a residential district in South London known for its Victorian architecture, local markets, and proximity to Brockwell Park.
-
E.
Burgess Hill
Burgess Hill is a town in southeastern England known as a commuter hub with residential areas and light industry, situated within the county of West Sussex.
- 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_69a88aa979788190ad6500f1d8eee2fc |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc0be7fb4819081a5f9c46b616bdb |
completed | March 7, 2026, 6:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afc629e4588190b6e56329809ed72d |
completed | March 10, 2026, 7:20 a.m. |
Created at: March 4, 2026, 7:47 p.m.