Triple

T21726699
Position Surface form Disambiguated ID Type / Status
Subject The Hermit E536291 entity
Predicate associatedWithPlanet P2830 FINISHED
Object Mercury 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: Mercury | Statement: [The Hermit, associatedWithPlanet, Mercury]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mercury
Context triple: [The Hermit, associatedWithPlanet, Mercury]
  • A. Mercury
    Mercury was an American automobile marque of the Ford Motor Company known for producing mid-priced cars positioned between Ford and Lincoln.
  • B. Mercury chosen
    Mercury is the smallest and innermost planet in our Solar System, known for its extreme temperature variations and heavily cratered surface.
  • C. Mercury
    Mercury is the nickname of former American football running back Eugene "Mercury" Morris, best known for his role on the undefeated 1972 Miami Dolphins team.
  • D. Mercury
    "Mercury" is an album by American rapper Khujo, known for its gritty Southern hip hop style and introspective lyricism.
  • E. Mercury
    Mercury is a software platform that serves as a backend or data management system commonly integrated with tools like the ConQuest search interface.
  • 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_69e0c46d3284819099a4f9d5a704eb95 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efd973ac648190bb09e20ac1be2d9b completed April 27, 2026, 9:47 p.m.
Created at: April 16, 2026, 6:48 p.m.