Triple

T15632160
Position Surface form Disambiguated ID Type / Status
Subject Karen Janney E375840 entity
Predicate workTitle P24259 FINISHED
Object Mao II E77312 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: Mao II | Statement: [Karen Janney, workTitle, Mao II]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mao II
Context triple: [Karen Janney, workTitle, Mao II]
  • A. Mao II chosen
    Mao II is a 1991 novel by Don DeLillo that explores themes of terrorism, mass media, and the diminishing power of the individual writer in a spectacle-driven world.
  • B. Mao Chang
    Mao Chang is an ancient Chinese scholar traditionally credited with producing one of the most influential commentaries on the Confucian classic "Book of Songs" (Shijing).
  • C. Mao
    Mao is an Omotic language spoken in southwestern Ethiopia, known for its complex tonal system and classification within the Afroasiatic language family.
  • D. Mao
    Mao is a common Chinese surname borne by numerous historical and contemporary figures across politics, culture, and society.
  • E. Mao Anlong
    Mao Anlong was one of Mao Zedong’s sons, who died in childhood and is less documented than his more politically prominent siblings.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eb7338881909f3c430bb73f91d1 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff997e13e4819080a39f59172ab99c completed May 9, 2026, 8:30 p.m.
Created at: April 10, 2026, 4:14 a.m.