Triple

T12232005
Position Surface form Disambiguated ID Type / Status
Subject Blade E291496 entity
Predicate affiliation P10 FINISHED
Object MI:13 E631492 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: MI:13 | Statement: [Blade, affiliation, MI:13]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MI:13
Context triple: [Blade, affiliation, MI:13]
  • A. MI:13 chosen
    MI:13 is a fictional British intelligence agency in Marvel Comics that specializes in supernatural and paranormal threats.
  • B. MI 79
    MI 79 is a class of electric multiple unit trains built for the Paris RER network, notably used on Line B.
  • C. MI 84
    MI 84 is a class of electric multiple unit trains used on the RER B commuter rail line in the Paris metropolitan area.
  • D. Operation MI
    Operation MI was the Imperial Japanese Navy’s World War II plan to seize Midway Atoll, culminating in the pivotal Battle of Midway in June 1942.
  • E. MI 09
    MI 09 is a modern dual-voltage electric multiple unit train used on the RER A commuter rail line in the Paris region.
  • 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_69d6ab668acc8190963ba424049d6aee completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91ca45bd48190b8b7f6b29b6bb25b completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60aad2d488190ba36588e3376ca1a completed May 2, 2026, 2:31 p.m.
Created at: April 8, 2026, 9:51 p.m.