Triple
T15297787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Downside School |
E365702
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Bristol |
E16444
|
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: Bristol | Statement: [Downside School, near, Bristol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bristol Context triple: [Downside School, near, Bristol]
-
A.
Bristol
Bristol is a historic borough in Bucks County, Pennsylvania, located along the Delaware River northeast of Philadelphia.
-
B.
Bristol
chosen
Bristol is a historic port city in southwest England known for its maritime heritage, vibrant cultural scene, and distinctive Georgian and Victorian architecture.
-
C.
Bristol
Bristol is a city in central Connecticut known for being the home of ESPN and for its historic clock-making industry.
-
D.
Bristol
Bristol is a city in central Connecticut known historically for its clock-making industry and as the longtime home of ESPN’s headquarters.
-
E.
Bristol
Bristol is a small town located in Dane County in the U.S. state of Wisconsin.
- 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_69d85a113ee881908e297a1d38dd79fa |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03686bfb8819080ba0caae652170a |
completed | April 16, 2026, 1:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feef61cf80819096a3cb611f5af9fc |
completed | May 9, 2026, 8:25 a.m. |
Created at: April 10, 2026, 3:15 a.m.