Triple

T6172344
Position Surface form Disambiguated ID Type / Status
Subject Loopt E137731 entity
Predicate competitor P1375 FINISHED
Object Foursquare E236192 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: Foursquare | Statement: [Loopt, competitor, Foursquare]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Foursquare
Context triple: [Loopt, competitor, Foursquare]
  • A. Foursquare chosen
    Foursquare is a location-based technology company best known for its mobile apps and platform that let users discover places, check in, and power location intelligence for businesses.
  • B. Foursquare
    Foursquare is a global Pentecostal Christian denomination known formally as the International Church of the Foursquare Gospel.
  • C. American Foursquare
    American Foursquare is a popular early-20th-century American residential architectural style characterized by a simple boxy form, two-and-a-half stories, a hipped roof, and a large front porch.
  • D. Square, Inc.
    Square, Inc. is a financial technology company best known for its mobile payment solutions and point-of-sale systems that enable businesses to accept electronic payments easily.
  • E. Nokia HERE Maps
    Nokia HERE Maps is a mapping and navigation service offering offline maps, turn-by-turn directions, and location-based features across multiple devices and platforms.
  • 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_69c008a68c508190a8d78245c865960e completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05d9319548190980c99f692bd4115 completed March 22, 2026, 9:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141ad559881909076b6ab34b14f2b completed March 23, 2026, 1:35 p.m.
Created at: March 22, 2026, 4:18 p.m.