Triple
T170367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Cam |
E3107
|
entity |
| Predicate | hasSection |
P35
|
FINISHED |
| Object | The Backs |
E9255
|
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: The Backs | Statement: [River Cam, hasSection, The Backs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Backs Context triple: [River Cam, hasSection, The Backs]
-
A.
The Backs
chosen
The Backs is a picturesque area in Cambridge where several historic college buildings back onto landscaped gardens along the River Cam.
-
B.
Lomond Hills
Lomond Hills is a prominent range of hills in central Scotland known for its scenic landscapes, walking trails, and panoramic views over Fife and the surrounding area.
-
C.
Cornerhouse
Cornerhouse was a renowned contemporary arts and cinema centre in Manchester, England, known for its independent film screenings, visual arts exhibitions, and cultural events.
-
D.
Silver Hill
Silver Hill is a small commuter rail station in Weston, Massachusetts, served by the MBTA's Fitchburg Line.
-
E.
Granta Park
Granta Park is a major science and business park in the Cambridge area, known for hosting high-tech and biotech companies within the broader Silicon Fen cluster.
- 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_69a2524ce1e48190ab066bf72859f474 |
completed | Feb. 28, 2026, 2:26 a.m. |
| NER | Named-entity recognition | batch_69a258b82bdc81908ebd50fb05d511df |
completed | Feb. 28, 2026, 2:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a2fa7ac14081908c0bf9512e85e18a |
completed | Feb. 28, 2026, 2:23 p.m. |
Created at: Feb. 28, 2026, 2:34 a.m.