Triple

T10205702
Position Surface form Disambiguated ID Type / Status
Subject Philip Armour E242187 entity
Predicate familyName P18 FINISHED
Object Armour E599513 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: Armour | Statement: [Philip Armour, familyName, Armour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Armour
Context triple: [Philip Armour, familyName, Armour]
  • A. Armour chosen
    Armour is a Scottish surname most famously associated with Jean Armour, the wife of poet Robert Burns.
  • B. Armills
    Armills are ceremonial arm bracelets traditionally worn by British monarchs during coronations as symbols of sincerity and wisdom.
  • C. ARMIR
    ARMIR was the Italian 8th Army deployed on the Eastern Front during World War II, best known for its disastrous defeat alongside German forces in the Soviet Union.
  • D. Aspis
    Aspis is an ancient Greek comedy by the playwright Menander, known for its exploration of family, inheritance, and social customs in Athenian society.
  • E. Burlington armour
    Burlington armour is a British-developed composite tank armour system, better known as Chobham armour, designed to provide enhanced protection against both kinetic and shaped-charge threats.
  • 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_69d381ae26c48190985abd0e25ee5d04 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d395f6298c8190a4a0ad9770f10e80 completed April 6, 2026, 11:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69d652b489608190b844e1199e6126ce completed April 8, 2026, 1:05 p.m.
Created at: April 6, 2026, 10:47 a.m.