Triple

T20180725
Position Surface form Disambiguated ID Type / Status
Subject A39 E492718 entity
Predicate connectsTown P845 FINISHED
Object Porlock 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: Porlock | Statement: [A39, connectsTown, Porlock]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porlock
Context triple: [A39, connectsTown, Porlock]
  • A. Porlock chosen
    Porlock is a coastal village in Somerset, England, known for its scenic setting on the edge of Exmoor National Park and its historic harbor.
  • B. Porlock Hill
    Porlock Hill is a famously steep and winding road in Somerset, England, known as one of the country’s most challenging and scenic driving climbs.
  • C. Potton
    Potton is a small market town in Bedfordshire, England, known for its historic town centre and rural surroundings.
  • D. Porlock Weir
    Porlock Weir is a small historic harbour hamlet on the coast of Somerset, England, known for its picturesque thatched cottages, pebble beach, and tidal harbour.
  • E. Warsop
    Warsop is a small town and civil parish in Nottinghamshire, England, historically linked to coal mining and situated near the larger market town of Mansfield.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e668eed2e88190b54b15e6545dbdf8 completed April 20, 2026, 5:57 p.m.
Created at: April 11, 2026, 11:36 p.m.