Triple

T18574325
Position Surface form Disambiguated ID Type / Status
Subject Snowden leaks E453947 entity
Predicate revealedProgram P38401 FINISHED
Object Tempora NE NERFINISHED

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: Tempora | Statement: [Snowden leaks, revealedProgram, Tempora]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tempora
Context triple: [Snowden leaks, revealedProgram, Tempora]
  • A. TEMPORA chosen
    TEMPORA is a British signals intelligence program run by GCHQ that intercepts and stores large volumes of internet and telecommunications data for analysis.
  • B. Tempi
    Tempi is a municipality in the Thessaly region of central Greece, known for its scenic location near the Vale of Tempe and along the Pinios River.
  • C. De tempore
    De tempore is a medieval theological work by Edmund of Abingdon that reflects his scholastic approach to Christian doctrine and moral teaching.
  • D. The Temp
    The Temp is a film directed by Tom Holland, best known for his work in the horror genre, including the cult classic Fright Night.
  • E. Zeitlofs
    Zeitlofs is a small municipality in the Bad Kissingen district of northern Bavaria, Germany, known for its rural setting within the Rhön region.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e543c8c0608190afc99235006bf87f completed April 19, 2026, 9:06 p.m.
Created at: April 10, 2026, 11:43 a.m.