Triple

T22068898
Position Surface form Disambiguated ID Type / Status
Subject Charles William Tanner E545352 entity
Predicate familyName P18 FINISHED
Object Tanner NE NERFINISHED

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: Tanner | Statement: [Charles William Tanner, familyName, Tanner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tanner
Context triple: [Charles William Tanner, familyName, Tanner]
  • A. Tanner chosen
    Tanner is a surname of Finnish origin, notably borne by the politician Väinö Tanner.
  • B. Tanner
    Tanner is a character appearing in the science fiction action film "Judgment Day," associated with its futuristic, apocalyptic storyline.
  • C. Tanner Buchanan
    Tanner Buchanan is an American actor best known for his roles in the series "Cobra Kai" and various film and television projects.
  • D. Tanner Sack
    Tanner Sack is a Remade dock worker in China Miéville’s novel "The Scar," known for his transformation into an amphibious being and his central role in the journey to the floating pirate city of Armada.
  • E. Marc Tanner
    Marc Tanner is a music producer and songwriter known for his work on various rock and pop albums, including projects like "After the Rain."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12885fe04819092cdde142f91e147 completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:28 p.m.