Triple

T20712752
Position Surface form Disambiguated ID Type / Status
Subject Pinterest, Inc. E509088 entity
Predicate tradedAs P2822 FINISHED
Object PINS 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: PINS | Statement: [Pinterest, Inc., tradedAs, PINS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PINS
Context triple: [Pinterest, Inc., tradedAs, PINS]
  • A. PINS chosen
    PINS is the stock ticker symbol for Pinterest, a visual discovery and social media platform where users find and save ideas through images and videos.
  • B. Pins-Justaret
    Pins-Justaret is a small commune in southwestern France, located in the Haute-Garonne department near Toulouse.
  • C. Pin
    Pin is a slender, pointed fastening device commonly used to secure or attach materials such as fabric or paper.
  • D. Pinnes
    Pinnes was an Illyrian king of the Ardiaei in the 3rd century BCE, known primarily as the young monarch whose reign was dominated by the regency of Queen Teuta and early conflicts with Rome.
  • E. PIN
    PIN is the commonly used abbreviation for People in Need, a humanitarian and development non-governmental organization.
  • 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_69e0b4c40ad88190b81f77695366d328 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1ce84e48190922db93ed4b5d21b completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:15 p.m.