Triple

T15454364
Position Surface form Disambiguated ID Type / Status
Subject La Garde E371729 entity
Predicate hadSubunit P28620 FINISHED
Object Middle Guard E371723 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: Middle Guard | Statement: [La Garde, hadSubunit, Middle Guard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Middle Guard
Context triple: [La Garde, hadSubunit, Middle Guard]
  • A. Middle Guard chosen
    The Middle Guard was a veteran formation within Napoleon’s Imperial Guard, composed of experienced soldiers who ranked between the elite Old Guard and the more numerous Young Guard in status and prestige.
  • B. Inner Guard
    The Inner Guard is a Masonic lodge officer responsible for guarding the entrance from within and controlling admission to meetings.
  • C. South Guard
    South Guard is a prominent peak in California’s Sierra Nevada range, located along the rugged Great Western Divide in Sequoia National Park.
  • D. On Guard
    On Guard is a popular-level Christian apologetics book by philosopher and theologian William Lane Craig that presents arguments for the rationality of the Christian faith.
  • E. On Guard
    On Guard is a 1997 French swashbuckling adventure film, based on Paul Féval’s novel "Le Bossu," known for its spirited swordplay, period setting, and blend of action, romance, and comedy.
  • 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_69d85cc8bd308190886949510b42e764 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f131b1481909ff099c3b844ee07 completed April 16, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff21b5e1788190bdc8182822f25fa1 completed May 9, 2026, 11:59 a.m.
Created at: April 10, 2026, 3:31 a.m.