Triple

T9955788
Position Surface form Disambiguated ID Type / Status
Subject FN FAL E195443 entity
Predicate manufacturer P490 FINISHED
Object FN Herstal E386645 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: FN Herstal | Statement: [FN FAL, manufacturer, FN Herstal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: FN Herstal
Context triple: [FN FAL, manufacturer, FN Herstal]
  • A. FN Herstal chosen
    FN Herstal is a Belgian firearms manufacturer renowned for producing a wide range of military and law-enforcement weapons used worldwide.
  • B. Rheinmetall
    Rheinmetall is a major German defense and automotive company best known for producing advanced military technologies, including the main armament and systems for modern battle tanks.
  • C. Steyr
    Steyr is a historic industrial city in northern Austria known for its well-preserved old town and long tradition of metalworking and manufacturing.
  • D. MOWAG
    MOWAG is a Swiss defense vehicle manufacturer best known for designing and producing the Piranha family of wheeled armored combat vehicles.
  • E. RCS Wavre
    RCS Wavre is a Belgian football club based in the town of Wavre, competing in the lower tiers of the national league system.
  • 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_69ca82eaaa008190a54fa1a9f954b9ad completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb69631d08190ab2b1d1c22d46da7 completed April 2, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23d71342081908084c27790ef4fcc completed April 5, 2026, 10:46 a.m.
Created at: March 30, 2026, 8:46 p.m.