Triple

T17290031
Position Surface form Disambiguated ID Type / Status
Subject OB Süd E419759 entity
Predicate subordinateTo P258 FINISHED
Object OKW E38766 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: OKW | Statement: [OB Süd, subordinateTo, OKW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OKW
Context triple: [OB Süd, subordinateTo, OKW]
  • A. OKW chosen
    OKW (Oberkommando der Wehrmacht) was the German Armed Forces High Command during Nazi Germany, overseeing the strategic direction and coordination of the Wehrmacht in World War II.
  • B. OKO
    OKO is the IATA airport code for Yokota Air Base, a United States Air Force installation in western Tokyo, Japan.
  • C. OKM
    OKM was the abbreviation for the Oberkommando der Marine, the supreme command authority of Nazi Germany’s Kriegsmarine (navy) during World War II.
  • D. OKS
    OKS is the abbreviation commonly used for the National Olympic Committee of Serbia, the body responsible for organizing the country’s participation in the Olympic Games.
  • E. OKL
    OKL was the supreme command authority of Nazi Germany’s Luftwaffe, overseeing its air force operations, organization, and strategy during World War II.
  • 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_69d886db32608190a61e18862c5a8af6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e43782b7ac8190b702567e9ccf9a35 completed April 19, 2026, 2:01 a.m.
NED1 Entity disambiguation (via context triple) batch_6a017959ffb0819099d70ed1541158ee completed May 11, 2026, 6:38 a.m.
Created at: April 10, 2026, 5:40 a.m.