Triple

T15379719
Position Surface form Disambiguated ID Type / Status
Subject SMS Markgraf E367766 entity
Predicate locationAfterWar P63221 FINISHED
Object interned at Scapa Flow LITERAL 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: interned at Scapa Flow | Statement: [SMS Markgraf, locationAfterWar, interned at Scapa Flow]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: locationAfterWar
Context triple: [SMS Markgraf, locationAfterWar, interned at Scapa Flow]
  • A. postWarLocation chosen
    Indicates the place where an entity is located or based after a war or major conflict has ended.
  • B. finalPreWarLocation
    Indicates the last known location of an entity immediately before the onset of a specified war or conflict.
  • C. countryAfterConflict
    Indicates that one country exists in a post-conflict state or status relative to a specified conflict or warring situation.
  • D. ownershipAfterWar
    Indicates that an entity comes to own or control another entity as a result of outcomes or arrangements following a war or armed conflict.
  • E. legalStatusAfterWar
    Indicates the legal condition or classification assigned to an entity as a consequence of, or following the conclusion of, a war or armed conflict.
  • F. None of above.

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_69d85a1551a08190ba2caea7cd51c639 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e6044488190b0499db109f7f821 completed April 16, 2026, 1:41 a.m.
PD Predicate disambiguation batch_69ded27742a881909cd73cc5c7d062fd completed April 14, 2026, 11:49 p.m.
Created at: April 10, 2026, 3:19 a.m.