Triple
T11825741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caxton House |
E281255
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Tothill Street |
E344377
|
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: Tothill Street | Statement: [Caxton House, location, Tothill Street]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tothill Street Context triple: [Caxton House, location, Tothill Street]
-
A.
Tothill Street
chosen
Tothill Street is a historic street in Westminster, central London, situated near the Houses of Parliament and notable government buildings.
-
B.
Eccleston Street
Eccleston Street is a road in central London’s Belgravia area, situated near Victoria and close to major landmarks such as Buckingham Palace.
-
C.
Margaret Street
Margaret Street is a fictional character from Toni Morrison’s novel "Tar Baby," representing complex themes of race, identity, and cultural dislocation.
-
D.
Margaret Street
Margaret Street is an individual known primarily as the spouse of Valerian Street.
-
E.
Great Russell Street
Great Russell Street is a central London thoroughfare in Bloomsbury best known as the location of the British Museum.
- 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_69d6ab276f8c8190b1966a0ef11349ac |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a5eb299481909de3c0e85628fbe4 |
completed | April 10, 2026, 7:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f739644ed48190896d7b2b6c3b5f8f |
completed | May 3, 2026, 12:02 p.m. |
Created at: April 8, 2026, 9:43 p.m.