Triple
T3307972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Granta |
E69496
|
entity |
| Predicate | hasMouthNear |
P350
|
FINISHED |
| Object | Cambridge |
E492
|
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: Cambridge | Statement: [River Granta, hasMouthNear, Cambridge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cambridge Context triple: [River Granta, hasMouthNear, Cambridge]
-
A.
Cambridge
Cambridge is a town in New Zealand known for its picturesque rural setting, equestrian culture, and proximity to the Waikato River.
-
B.
Cambridge, England
chosen
Cambridge, England is a historic university city on the River Cam renowned for the University of Cambridge and its longstanding contributions to education, science, and culture.
-
C.
Oxford
Oxford is a historic English city renowned for its prestigious university, distinctive architecture, and long-standing academic and cultural influence.
-
D.
Oxford
Oxford is a federal electoral district in Ontario, Canada, represented in the House of Commons.
-
E.
Oxford
Oxford is a small town in New Haven County, Connecticut, known for its suburban-rural character and growing residential communities.
- 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_69ad859f218081909458d2cebbf57565 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0cc15088190b51c311c6590df04 |
completed | March 8, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b32507bc808190b9c3fce4c456b0aa |
completed | March 12, 2026, 8:41 p.m. |
Created at: March 8, 2026, 3:11 p.m.