Triple
T7979875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernicia |
E185543
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Deira |
E182341
|
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: Deira | Statement: [Bernicia, borders, Deira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deira Context triple: [Bernicia, borders, Deira]
-
A.
Deira
chosen
Deira was an early medieval Anglo-Saxon kingdom in what is now northern England, later incorporated into the larger kingdom of Northumbria.
-
B.
Deira
Deira is one of Dubai’s oldest commercial and residential districts, known for its traditional souks, historic waterfront, and role as a former trading hub of the city.
-
C.
Hamad Town
Hamad Town is a planned residential town in Bahrain known for its large roundabouts and diverse, predominantly middle-class population.
-
D.
Kalba
Kalba is a coastal town and exclave of the Emirate of Sharjah in the United Arab Emirates, known for its mangrove forests and tranquil beaches along the Gulf of Oman.
-
E.
Luwan District
Luwan District was a former central district of Shanghai, China, known for its historic architecture, commercial streets, and cultural landmarks on the Puxi side of the 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_69ca829851908190b4e03829353ee7c3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c261904819086910898071f3629 |
completed | March 31, 2026, 3:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe0d3c724819087df03cea2ed998f |
completed | March 31, 2026, 2:57 p.m. |
Created at: March 30, 2026, 5:14 p.m.