Triple
T1722855
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dunkin' Park |
E37430
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Hartford |
E67626
|
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: Hartford | Statement: [Dunkin' Park, city, Hartford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hartford Context triple: [Dunkin' Park, city, Hartford]
-
A.
Hartford
chosen
Hartford is the capital city of Connecticut and a historic center of insurance, government, and culture in the northeastern United States.
-
B.
Hartford (Providence)
Hartford is a neighborhood in the city of Providence, Rhode Island, known as a residential area within Providence County.
-
C.
The Hartford
The Hartford is a major American insurance and financial services company known for its property and casualty, group benefits, and mutual funds offerings.
-
D.
New Haven, Connecticut
New Haven, Connecticut is a historic coastal city in southern New England best known as the home of Yale University and a major center of education, culture, and research.
-
E.
Meriden
Meriden is a city in central Connecticut known for its historic silver manufacturing industry and landmarks like Castle Craig in Hubbard Park.
- 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_69a8861acab88190bb43cde203429399 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa63587ce08190a6a9e6dae11a708c |
completed | March 6, 2026, 5:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bda3e679a881908f91a36675037d1a |
completed | March 20, 2026, 7:45 p.m. |
Created at: March 4, 2026, 7:30 p.m.