Triple

T5924679
Position Surface form Disambiguated ID Type / Status
Subject Eric Armstrong E131777 entity
Predicate sibling P363 FINISHED
Object Karen Armstrong E3084 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: Karen Armstrong | Statement: [Eric Armstrong, sibling, Karen Armstrong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Armstrong
Context triple: [Eric Armstrong, sibling, Karen Armstrong]
  • A. Karen Armstrong chosen
    Karen Armstrong is a British author and former nun renowned for her influential books on comparative religion and the history of faith.
  • B. Karen Armstrong
    Karen Armstrong is the daughter of American astronaut Neil Armstrong, the first person to walk on the Moon.
  • C. Antonia Fraser
    Antonia Fraser is a British historian and biographer renowned for her popular works on European royalty and major figures of British history.
  • D. Eve Peabody
    Eve Peabody is the charming, quick-witted American showgirl at the center of the 1939 romantic comedy film "Midnight," whose misadventures in Paris drive the film’s plot.
  • E. Claire Tomalin
    Claire Tomalin is a British literary journalist and acclaimed biographer known for her works on figures such as Charles Dickens, Samuel Pepys, and Jane Austen.
  • 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_69c0085b75e88190a632f9691f9da48b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c03852806c81908ba726c16adf3358 completed March 22, 2026, 6:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0c0483e3481908e50f8b34b11a878 completed March 23, 2026, 4:23 a.m.
Created at: March 22, 2026, 4 p.m.