Triple

T35959656
Position Surface form Disambiguated ID Type / Status
Subject Summit E1039959 entity
Predicate previousWorldsFastestSupercomputer P184899 FINISHED
Object Sunway TaihuLight 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: Sunway TaihuLight | Statement: [Summit, previousWorldsFastestSupercomputer, Sunway TaihuLight]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: previousWorldsFastestSupercomputer
Context triple: [Summit, previousWorldsFastestSupercomputer, Sunway TaihuLight]
  • A. fastestComputerFrom
    Indicates that one entity is the fastest computer originating from, or associated with, a specified source, group, or location.
  • B. fastestComputerUntil chosen
    Indicates that a computer was the fastest among all computers up to (and possibly including) a specified point in time.
  • C. supercomputerName
    Indicates that an entity has the specified name used to identify it as a supercomputer.
  • D. hasSupercomputer
    Indicates that an entity possesses, controls, or is equipped with a supercomputer.
  • E. top500List
    Indicates that an entity is included in a ranking or compilation of the top 500 items within a particular domain or category.
  • F. None of above.

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_69f76e26b21081909fd9ffb3aff6c77a completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69ff80d9a1d88190a95b1488acd6e2e5 completed May 9, 2026, 6:45 p.m.
PD Predicate disambiguation batch_69ff802ae2dc819093a3cda42b63dcbd completed May 9, 2026, 6:42 p.m.
Created at: May 3, 2026, 4:07 p.m.