Triple

T8005196
Position Surface form Disambiguated ID Type / Status
Subject Roger McNamee E186346 entity
Predicate earlyInvestorIn P23259 FINISHED
Object Facebook E1582 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: Facebook | Statement: [Roger McNamee, earlyInvestorIn, Facebook]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Facebook
Context triple: [Roger McNamee, earlyInvestorIn, Facebook]
  • A. Facebook chosen
    Facebook is a major global social networking platform that allows users to connect, share content, and communicate online.
  • B. Facebook Portal
    Facebook Portal is a line of smart video-calling devices developed by Meta (formerly Facebook), designed to facilitate hands-free, AI-enhanced communication in the home.
  • C. Meta Platforms, Inc.
    Meta Platforms, Inc. is a major American technology company best known as the parent of Facebook, Instagram, WhatsApp, and other social media and virtual reality products.
  • D. Bebo
    Bebo is a now-defunct social networking website that was especially popular in the mid-2000s for sharing profiles, photos, and messages among friends.
  • E. FB
    FB is the common abbreviation for Fenerbahçe SK, one of Turkey’s most prominent multi-sport clubs best known for its successful football team based in Istanbul.
  • 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_69ca82aaaf24819084b94d18f699ba53 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3cf5fb588190ada4ec7d8087619c completed March 31, 2026, 3:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe019a094819082baecdcb007c84f completed March 31, 2026, 2:54 p.m.
Created at: March 30, 2026, 5:18 p.m.