Triple

T1673820
Position Surface form Disambiguated ID Type / Status
Subject Eccles tram stop E36184 entity
Predicate hasRailCode P18202 FINISHED
Object ECC E186987 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: ECC | Statement: [Eccles tram stop, hasRailCode, ECC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ECC
Context triple: [Eccles tram stop, hasRailCode, ECC]
  • A. ECC chosen
    ECC is the National Rail station code for Eccles railway station in Greater Manchester, England.
  • B. ECCAS
    ECCAS (Economic Community of Central African States) is a regional economic community that promotes economic integration, peace, and development among Central African countries.
  • C. ECA
    The Economic Cooperation Administration (ECA) was the U.S. government agency responsible for administering the Marshall Plan to aid European economic recovery after World War II.
  • D. ECA
    ECA is a regional United Nations commission focused on promoting economic and social development across the African continent.
  • E. ECA
    The ECA is the European Union institution responsible for auditing the EU’s finances and ensuring that its budget is correctly implemented.
  • 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_69a8861286808190939afff3ce8ee31e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa6246753081909dace4eacf9cb1c0 completed March 6, 2026, 5:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad71b341bc8190b79f76f426dfa7dd completed March 8, 2026, 12:55 p.m.
Created at: March 4, 2026, 7:29 p.m.