Triple
T13110813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Floating Harbour |
E310964
|
entity |
| Predicate | separatedBy |
P1175
|
FINISHED |
| Object | New Cut |
E1023078
|
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: New Cut | Statement: [Floating Harbour, separatedBy, New Cut]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: New Cut Context triple: [Floating Harbour, separatedBy, New Cut]
-
A.
New Cut
chosen
New Cut is an artificial waterway in Bristol, England, constructed in the early 19th century to divert the River Avon and improve the city’s harbour.
-
B.
The Cut
The Cut is a street in the Waterloo area of London known for its theatres, restaurants, and proximity to major transport links.
-
C.
The Cut
The Cut is a digital publication and vertical of New York Magazine that focuses on fashion, culture, politics, and women’s issues.
-
D.
The Cut
The Cut is a 2014 historical drama film directed by Fatih Akin that follows an Armenian man's search for his daughters in the aftermath of the Armenian genocide.
-
E.
In the Cut
In the Cut is a 2003 neo-noir erotic thriller film directed by Jane Campion, known for its gritty exploration of female sexuality and urban violence in contemporary New York City.
- 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_69d806a872d08190a329806f8ff30df4 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9817e4f408190b77c198b4157d77a |
completed | April 10, 2026, 11:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6eadad81c8190881e6577e1c2a207 |
completed | May 3, 2026, 6:27 a.m. |
Created at: April 9, 2026, 9:05 p.m.