Triple

T9543493
Position Surface form Disambiguated ID Type / Status
Subject Kim Philby E230221 entity
Predicate familyName P18 FINISHED
Object Philby E230221 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: Philby | Statement: [Kim Philby, familyName, Philby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philby
Context triple: [Kim Philby, familyName, Philby]
  • A. Kim Philby chosen
    Kim Philby was a high-ranking British intelligence officer who became one of the most infamous Soviet double agents of the 20th century.
  • B. Colonel Redl
    Colonel Redl is a 1985 historical drama film by István Szabó that portrays the rise and tragic downfall of an Austro-Hungarian officer entangled in espionage and political intrigue before World War I.
  • C. Christian Spies
    Christian Spies is a notable individual who shares the surname Spies and is recognized as a distinguished bearer of that name.
  • D. James Jesus Angleton
    James Jesus Angleton was a prominent American intelligence officer best known for serving as the long-time chief of counterintelligence at the CIA during the Cold War.
  • E. Le Chiffre
    Le Chiffre is a notorious villain in the James Bond universe, best known as the primary antagonist and high-stakes gambler in Ian Fleming’s novel and its film adaptations.
  • 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_69ca847c70b8819088a0a0bad64a50d6 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd98e9be048190bf1f01884ff7c362 completed April 1, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1527c0914819087ffa9d201afdd35 completed April 4, 2026, 6:03 p.m.
Created at: March 30, 2026, 8:01 p.m.