Triple
T15705879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horse Guards Avenue |
E380707
|
entity |
| Predicate | hasJunctionWith |
P1018
|
FINISHED |
| Object | Whitehall |
E16070
|
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: Whitehall | Statement: [Horse Guards Avenue, hasJunctionWith, Whitehall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Whitehall Context triple: [Horse Guards Avenue, hasJunctionWith, Whitehall]
-
A.
Whitehall
chosen
Whitehall is the central London district that serves as the administrative heart of the United Kingdom, housing many key government departments and ministries.
-
B.
Whitehall
Whitehall is a small town in upstate New York that serves as a regional rail stop and gateway between New York and Vermont.
-
C.
Whitehall
Whitehall is a grand Gilded Age mansion in Palm Beach, Florida, built by Henry Flagler and now preserved as the Flagler Museum.
-
D.
Whitehall
Whitehall is a suburban borough in Allegheny County, Pennsylvania, located just south of Pittsburgh.
-
E.
Whitehall
Whitehall is a small coastal settlement on the Orkney island of Stronsay in Scotland.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f70d44c81909edba6bd4b58b1c5 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82f05d648190a0c73b60dc027287 |
completed | May 9, 2026, 6:54 p.m. |
Created at: April 10, 2026, 4:45 a.m.