Triple
T16066352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hammersmith Embankment |
E389741
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Upper Mall |
E725212
|
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: Upper Mall | Statement: [Hammersmith Embankment, adjacentTo, Upper Mall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Upper Mall Context triple: [Hammersmith Embankment, adjacentTo, Upper Mall]
-
A.
Upper Mall
chosen
Upper Mall is a historic riverside street in Hammersmith, London, lined with notable period houses and overlooking the River Thames.
-
B.
High Street Mall
High Street Mall is a local shopping centre in Portadown, County Armagh, Northern Ireland, offering a range of retail stores and services to the surrounding community.
-
C.
Bow Street Mall
Bow Street Mall is a major shopping centre located in the city of Lisburn, Northern Ireland, featuring a range of retail stores and services.
-
D.
Fort Street Mall
Fort Street Mall is a pedestrian-only shopping and business corridor in downtown Honolulu known for its retail stores, eateries, and proximity to offices and campuses.
-
E.
Broad Street Mall
Broad Street Mall is a major indoor shopping centre in Reading, England, featuring a range of retail stores, services, and eateries.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1837ca628819081dfc439fe322d58 |
completed | April 17, 2026, 12:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeb8cca308190875432a5cf5f8616 |
completed | May 10, 2026, 2:21 a.m. |
Created at: April 10, 2026, 4:57 a.m.