Triple

T143878
Position Surface form Disambiguated ID Type / Status
Subject Carl Sagan E2910 entity
Predicate familyName P18 FINISHED
Object Sagan E10635 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: Sagan | Statement: [Carl Sagan, familyName, Sagan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sagan
Context triple: [Carl Sagan, familyName, Sagan]
  • A. Bardeen
    Bardeen is a surname most notably associated with John Bardeen, the American physicist who won the Nobel Prize in Physics twice for his work on the transistor and superconductivity.
  • B. Nick Sagan chosen
    Nick Sagan is an American science fiction writer and screenwriter, known for his work on television series like Star Trek and for being the son of astronomer Carl Sagan.
  • C. Dorion Sagan
    Dorion Sagan is an American science writer and essayist known for his works on evolution, ecology, and complexity, and for coauthoring influential books with his mother, biologist Lynn Margulis.
  • D. Gaia
    Gaia is the primordial Greek earth goddess, revered as the ancestral mother of all life and the personification of the Earth itself.
  • E. Kosmos
    Kosmos is Alexander von Humboldt’s multi-volume work that presents a comprehensive scientific and philosophical overview of the natural world and the universe.
  • 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_69a2521e35c08190b28e5c9f1e3c9b59 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257caf678819092e975d5167f9df4 completed Feb. 28, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2bf691a848190a4f6e40d9aea2168 completed Feb. 28, 2026, 10:11 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.