Triple
T12229323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sheung Wan |
E291433
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Central |
E685608
|
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: Central | Statement: [Sheung Wan, borderedBy, Central]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Central Context triple: [Sheung Wan, borderedBy, Central]
-
A.
Central
Central is a subway station on the Massachusetts Bay Transportation Authority (MBTA) system located in Cambridge, Massachusetts.
-
B.
Central
Central is a former British ITV regional television company that served the Midlands region and produced a wide range of popular UK programming.
-
C.
Central
Central is the standard map abbreviation used to denote the Central line, one of the primary east–west routes on the London Underground.
-
D.
Central
chosen
Central is Hong Kong's primary central business district, known for its dense skyline, major financial institutions, and role as a commercial and political hub.
-
E.
Centre
Centre was the former name of the administrative region in central France now known as Centre-Val de Loire.
- 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_69d6ab668acc8190963ba424049d6aee |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91ca34fe88190900c8791c70948b7 |
completed | April 10, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f60aab4a70819099856b990e3a8a1b |
completed | May 2, 2026, 2:31 p.m. |
Created at: April 8, 2026, 9:51 p.m.