Triple
T17818313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UConn School of Law |
E444905
|
entity |
| Predicate | city |
P40
|
FINISHED |
| Object | Hartford |
—
|
NE NERFINISHED |
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: [UConn School of Law, city, Hartford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hartford Context triple: [UConn School of Law, 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
Hartford is a small city in eastern South Dakota that functions as a suburban community within the greater Sioux Falls metropolitan area.
-
C.
New Haven
New Haven is a small city in central Kentucky known for its historic railroad heritage and proximity to the Kentucky Railway Museum.
-
D.
Hartford (Providence)
Hartford is a neighborhood in the city of Providence, Rhode Island, known as a residential area within Providence County.
-
E.
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.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f0de78819099395b14db75a8a6 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e488812df081909771d51c54c405fe |
completed | April 19, 2026, 7:47 a.m. |
Created at: April 10, 2026, 10:14 a.m.