Triple

T11517931
Position Surface form Disambiguated ID Type / Status
Subject Don Burgess E273079 entity
Predicate workedOn P3 FINISHED
Object Contact E321116 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: Contact | Statement: [Don Burgess, workedOn, Contact]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Contact
Context triple: [Don Burgess, workedOn, Contact]
  • A. Contact
    Contact is a science fiction novel by Carl Sagan that explores humanity’s first communication with an extraterrestrial intelligence and the intersection of science, faith, and politics.
  • B. Contact chosen
    Contact is a 1997 science fiction film, based on Carl Sagan’s novel, that follows a scientist’s first-contact encounter with extraterrestrial intelligence.
  • C. Contact
    Contact is a large-scale immersive art installation by Icelandic-Danish artist Olafur Eliasson that explores perception, light, and spatial experience.
  • D. Contact!
    "Contact!" is the follow-up studio album by the French electronic music duo Blue, continuing their blend of synth-driven pop and dance sounds.
  • E. Contact Press
    Contact Press was a small but influential Canadian literary publishing house known for championing early works by major poets, including Leonard Cohen.
  • 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_69d6aae2c3748190bed2ea50dfb160dc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fcf927081908ef89eff7ad833b0 completed April 10, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e62530a6b08190a8ba3c410e79cf72 completed April 20, 2026, 1:08 p.m.
Created at: April 8, 2026, 9:36 p.m.