Triple

T13901686
Position Surface form Disambiguated ID Type / Status
Subject William M. Evarts E334237 entity
Predicate familyName P18 FINISHED
Object Evarts E334237 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: Evarts | Statement: [William M. Evarts, familyName, Evarts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evarts
Context triple: [William M. Evarts, familyName, Evarts]
  • A. Evarts chosen
    Evarts is a surname most notably associated with William M. Evarts, a prominent 19th-century American lawyer, statesman, and U.S. Secretary of State.
  • B. Paxton
    Paxton is a small rural village in the Scottish Borders region of southeastern Scotland.
  • C. Paxton
    Paxton is a surname most prominently associated with the late American actor and filmmaker Bill Paxton, known for his roles in films like "Twister," "Aliens," and "Titanic."
  • D. Paxton
    Paxton is a central character in the horror film "Hostel," portrayed as an American tourist whose vacation in Europe turns into a brutal fight for survival.
  • E. Lausus
    Lausus was a high-ranking Byzantine court official and chamberlain under Emperor Theodosius II, known as a patron of Christian literature and monasticism.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de25d9c7a48190ad8fb0ca676f4f7b completed April 14, 2026, 11:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce7419cc81909488871c16d6b356 completed May 3, 2026, 10:38 p.m.
Created at: April 9, 2026, 10:15 p.m.