Triple
T4999759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jersey Marine Tower |
E112339
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Jersey Marine |
E112339
|
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: Jersey Marine | Statement: [Jersey Marine Tower, locatedIn, Jersey Marine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jersey Marine Context triple: [Jersey Marine Tower, locatedIn, Jersey Marine]
-
A.
Jersey Marine
chosen
Jersey Marine is a coastal village in South Wales known for its proximity to Swansea Bay and its historic tower landmark.
-
B.
Speirs + Major
Speirs + Major is a renowned UK-based lighting design practice known for creating innovative architectural and urban lighting schemes for landmark projects worldwide.
-
C.
Atlantic Marine
Atlantic Marine is a shipbuilding company known for constructing specialized research and commercial vessels.
-
D.
Wherry Lines
The Wherry Lines are a network of scenic railway routes in Norfolk, England, connecting Norwich with coastal towns such as Great Yarmouth and Lowestoft through the Broads.
-
E.
Hornblower Group
Hornblower Group is a U.S.-based maritime hospitality and transportation company known for operating sightseeing cruises, ferries, and experiential travel services in major cities and tourist destinations.
- 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_69bd4432b32c81909f3b3c6bd10f0653 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd72bc100c81908c3e02726e1ef8f6 |
completed | March 20, 2026, 4:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be8a38484881909893e5450dc33265 |
completed | March 21, 2026, 12:08 p.m. |
Created at: March 20, 2026, 1:34 p.m.