Triple

T16850195
Position Surface form Disambiguated ID Type / Status
Subject Alphabet Other Bets E409654 entity
Predicate includesBusiness P110112 FINISHED
Object Loon E184198 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: Loon | Statement: [Alphabet Other Bets, includesBusiness, Loon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Loon
Context triple: [Alphabet Other Bets, includesBusiness, Loon]
  • A. Loon chosen
    Loon was an experimental Alphabet project that aimed to provide internet connectivity to remote and underserved regions using high-altitude balloons.
  • B. Loon
    Loon is a historic medieval county in what is now eastern Belgium, centered around the city of Borgloon and influential in the region’s feudal politics.
  • C. Loons
    Loons is the nickname of Minnesota United FC, a Major League Soccer club based in Minnesota.
  • D. Bico de Pato
    Bico de Pato is a tight, slow-speed hairpin-style corner at Brazil’s Autódromo José Carlos Pace (Interlagos) known for heavy braking and overtaking opportunities.
  • E. Birdo
    Birdo is a recurring character in the Mario franchise, typically depicted as a pink, bow-wearing creature that shoots eggs from its mouth and appears as both an enemy and playable character in various games.
  • 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b378dda48190ab81d75f2cfe3ab3 completed April 18, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb1f02648190937c692af83843dc completed May 10, 2026, 5:06 p.m.
Created at: April 10, 2026, 5:24 a.m.