Triple

T8456802
Position Surface form Disambiguated ID Type / Status
Subject HSL 1 E199938 entity
Predicate owner P347 FINISHED
Object Infrabel E322969 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: Infrabel | Statement: [HSL 1, owner, Infrabel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Infrabel
Context triple: [HSL 1, owner, Infrabel]
  • A. Infrabel chosen
    Infrabel is the Belgian railway infrastructure manager responsible for the construction, maintenance, and operation of the national rail network.
  • B. SNCB/NMBS
    SNCB/NMBS is the Belgian national railway company responsible for operating most passenger train services and managing much of the rail infrastructure in Belgium.
  • C. Société des Transports Intercommunaux de Bruxelles
    The Société des Transports Intercommunaux de Bruxelles (STIB/MIVB) is the main public transport operator in Brussels, managing the city’s metro, tram, and bus networks.
  • D. Intercity Brussels
    Intercity Brussels is an international high-speed train service connecting the Netherlands with Brussels in Belgium.
  • E. STIB-MIVB
    STIB-MIVB is the primary public transport company in Brussels, Belgium, operating the city’s metro, tram, and bus networks.
  • 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_69ca8318231881908fd1bc1c4d45d286 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe48f180c8190a71cf9d7248ade60 completed March 31, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce4dd244988190904b0df97016ae13 completed April 2, 2026, 11:06 a.m.
Created at: March 30, 2026, 6:10 p.m.