Triple

T21169620
Position Surface form Disambiguated ID Type / Status
Subject Signal E521658 entity
Predicate developer P73 FINISHED
Object Signal Foundation 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: Signal Foundation | Statement: [Signal, developer, Signal Foundation]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Signal Foundation
Context triple: [Signal, developer, Signal Foundation]
  • A. Signal
    Signal is a toothpaste and oral care brand known for its focus on dental hygiene products in various international markets.
  • B. Signal
    Signal is a Canadian publishing imprint known for releasing thought-provoking non-fiction works on contemporary issues.
  • C. Signal
    Signal is the superhero alias of Duke Thomas, a member of the Batman Family who operates as a daytime vigilante in Gotham City.
  • D. Signal chosen
    Signal is a privacy-focused messaging app known for its strong end-to-end encryption and open-source protocol.
  • E. Signal Peak
    Signal Peak is the highest summit in Arizona’s Pinal Mountains, known for its forested slopes and panoramic views of the surrounding desert landscape.
  • 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_69e0b50e30748190b186824a206d39b9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72711be9481909f16107b71d3500a completed April 21, 2026, 7:28 a.m.
Created at: April 16, 2026, 3 p.m.