Triple

T4571517
Position Surface form Disambiguated ID Type / Status
Subject A322 road E123040 entity
Predicate serves P98 FINISHED
Object Lightwater E20311 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: Lightwater | Statement: [A322 road, serves, Lightwater]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lightwater
Context triple: [A322 road, serves, Lightwater]
  • A. Lightwater chosen
    Lightwater is a village and civil parish in the English county of Surrey, known for its residential character and proximity to heathland and countryside.
  • B. Openwater
    Openwater is a medical imaging and neurotechnology company developing high-resolution, low-cost brain and body imaging devices using novel optics and holography techniques.
  • C. King Water
    King Water is a small river in Cumbria, England, that serves as one of the tributaries feeding into the River Eden.
  • D. Old Water
    Old Water is a minor river in northern England that serves as one of the tributaries feeding into the River Eden.
  • E. Achterwasser
    Achterwasser is a coastal lagoon on the German island of Usedom, connected to the Baltic Sea and known for its shallow waters and scenic natural surroundings.
  • 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_69bd46466c7081909d07f36be2d08804 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd58c5afa48190bb8505e2cc16e89f completed March 20, 2026, 2:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69bde08756548190bb8433854c3efe01 completed March 21, 2026, 12:04 a.m.
Created at: March 20, 2026, 1:10 p.m.