Triple
T1424857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Jersey |
E30306
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Trenton |
E36449
|
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: Trenton | Statement: [New Jersey, capital, Trenton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trenton Context triple: [New Jersey, capital, Trenton]
-
A.
Trenton, New Jersey
chosen
Trenton, New Jersey is the capital city of the state of New Jersey, located along the Delaware River between New York City and Philadelphia.
-
B.
Newark
Newark is a small suburban city in California’s San Francisco Bay Area, located near the southern end of the East Bay.
-
C.
Newark
Newark is a major city in northern New Jersey known for its historic significance, diverse communities, and role as a cultural and transportation hub in the New York metropolitan area.
-
D.
Newark
Newark was the early colonial town that served as the first capital of Upper Canada, located at the mouth of the Niagara River (now known as Niagara-on-the-Lake, Ontario).
-
E.
Camden
Camden is a vibrant inner borough of London known for its alternative culture, markets, live music venues, and canalside atmosphere.
- 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_69a498fb823c8190a67ce4c4837e641a |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c4bd59148190b96f9f585e07aa0d |
completed | March 1, 2026, 10:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58a7b1fc8190b76b09e64097b881 |
completed | March 9, 2026, 5:20 a.m. |
Created at: March 1, 2026, 8 p.m.