Triple
T12776175
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frances Osborne |
E305377
|
entity |
| Predicate | hasWrittenWork |
P4
|
FINISHED |
| Object | Park Lane |
E78086
|
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: Park Lane | Statement: [Frances Osborne, hasWrittenWork, Park Lane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Park Lane Context triple: [Frances Osborne, hasWrittenWork, Park Lane]
-
A.
Park Lane
Park Lane is a prominent shopping and commercial area in the Whitefield district of Greater Manchester, England, featuring a variety of retail stores and local businesses.
-
B.
Park Lane
chosen
Park Lane is a major road in central London known for its luxury hotels, upscale residences, and proximity to Hyde Park.
-
C.
Park Lane
Park Lane is the main shopping street and commercial hub of the town of Poynton in Cheshire, England.
-
D.
Park Crescent
Park Crescent is a grand, Regency-era crescent of stuccoed terraced houses in London, designed by architect John Nash as part of his masterplan for Regent’s Park.
-
E.
Holland Park Avenue
Holland Park Avenue is a major tree-lined thoroughfare in west London, known for its elegant residential buildings, shops, and proximity to Holland Park.
- 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_69d7bdf2b43c819098ae5aa68e61ea58 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96df6b3c88190b0bbe70de8ddcbf3 |
completed | April 10, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f684fee60c81909245d4d70c9338c0 |
completed | May 2, 2026, 11:13 p.m. |
Created at: April 9, 2026, 5:29 p.m.