Triple

T21070124
Position Surface form Disambiguated ID Type / Status
Subject Terminus E519081 entity
Predicate hasTitle P38 FINISHED
Object Terminus 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: Terminus | Statement: [Terminus, hasTitle, Terminus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminus
Context triple: [Terminus, hasTitle, Terminus]
  • A. Terminus
    Terminus is the final installment of the French post-apocalyptic graphic novel series "Le Transperceneige," continuing its bleak exploration of class struggle aboard a perpetually moving train.
  • B. Terminus
    Terminus was the original 19th-century name for the settlement that later became the city of Atlanta, Georgia.
  • C. Terminus
    "Terminus" is a poem by Seamus Heaney, featured in his collection *The Haw Lantern*, that reflects on themes of borders, identity, and historical division.
  • D. Terminus
    Terminus is the remote frontier planet that serves as the capital of the Foundation in Isaac Asimov’s science fiction series.
  • E. Terminus
    Terminus is the Roman god who presides over boundaries and boundary markers, symbolizing the protection and sanctity of property lines.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69e0b505ef108190b25dd4033e2ff7eb completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6feb7b1d081909363c8bff785164b completed April 21, 2026, 4:36 a.m.
Created at: April 16, 2026, 2:46 p.m.