Triple

T15312427
Position Surface form Disambiguated ID Type / Status
Subject Constance Wu E366069 entity
Predicate hasSocialMediaProfile P57 FINISHED
Object Instagram E5329 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: Instagram | Statement: [Constance Wu, hasSocialMediaProfile, Instagram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Instagram
Context triple: [Constance Wu, hasSocialMediaProfile, Instagram]
  • A. Instagram chosen
    Instagram is a popular photo and video sharing social media platform known for its visual content, stories, and influencer culture.
  • B. Instagram main feed
    Instagram main feed is the primary scrolling interface in the Instagram app where users view a curated stream of posts, including photos, videos, and Reels, from accounts they follow and recommended content.
  • C. Instagram Direct
    Instagram Direct is Instagram’s built-in private messaging feature that lets users send direct messages, photos, videos, and other content to individuals or groups.
  • D. Facebook
    Facebook is a major global social networking platform that allows users to connect, share content, and communicate online.
  • E. Pinterest
    Pinterest is a visual discovery and bookmarking platform where users save and organize images and ideas into themed collections called boards.
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03cd2d5a88190aead748920f93d47 completed April 16, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef89d961481909be8dcc2864982c9 completed May 9, 2026, 9:04 a.m.
Created at: April 10, 2026, 3:16 a.m.