Triple

T9521082
Position Surface form Disambiguated ID Type / Status
Subject Finnieston E229644 entity
Predicate adjacentTo P224 FINISHED
Object Anderston E442762 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: Anderston | Statement: [Finnieston, adjacentTo, Anderston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anderston
Context triple: [Finnieston, adjacentTo, Anderston]
  • A. Anderston chosen
    Anderston is a district in Glasgow, Scotland, known for its central location near the River Clyde and mix of residential, commercial, and transport links.
  • B. Kelvinside
    Kelvinside is an affluent residential district in Glasgow, Scotland, known for its Victorian architecture, leafy streets, and proximity to the River Kelvin.
  • C. Garnethill
    Garnethill is a central Glasgow district known for its cultural institutions, historic tenements, and vibrant arts scene.
  • D. Glasgow Shettleston
    Glasgow Shettleston is a Scottish Parliament constituency in the east end of Glasgow, covering areas such as Shettleston and Parkhead.
  • E. Baillieston
    Baillieston is a residential suburb in the east end of Glasgow, Scotland, situated near major transport routes including the M73 motorway.
  • 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_69ca847870a881909d8d751a7d29da39 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9884dd5c8190b69c178cb2ac75c2 completed April 1, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69d190d2397081909127cb356b956f35 completed April 4, 2026, 10:29 p.m.
Created at: March 30, 2026, 7:59 p.m.