Triple

T38623
Position Surface form Disambiguated ID Type / Status
Subject Elon Musk E764 entity
Predicate coFounded P104 FINISHED
Object Zip2
Zip2 was an early online city guide and business directory software company from the late 1990s that provided web-based publishing tools for newspapers.
E3340 NE FINISHED

How this triple was built (4 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: Zip2 | Statement: [Elon Musk, coFounded, Zip2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zip2
Context triple: [Elon Musk, coFounded, Zip2]
  • A. Blitz
    The Blitz was the sustained German bombing campaign against the United Kingdom, particularly London, during 1940–1941 in World War II.
  • B. Metro
    Metro is the rapid transit system serving the Washington, D.C. metropolitan area, operated by the Washington Metropolitan Area Transit Authority (WMATA).
  • C. ARC
    ARC is the commonly used acronym for the Augmentation Research Center, a pioneering research group known for its early work on interactive computing and human–computer interaction.
  • D. HUP
    HUP is a major academic medical center in Philadelphia that serves as the flagship teaching hospital of the University of Pennsylvania's health system.
  • E. Ventra
    Ventra is the contactless fare payment system used across Chicago’s public transit network, including buses and trains.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Zip2
Triple: [Elon Musk, coFounded, Zip2]
Generated description
Zip2 was an early online city guide and business directory software company from the late 1990s that provided web-based publishing tools for newspapers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Zip2
Target entity description: Zip2 was an early online city guide and business directory software company from the late 1990s that provided web-based publishing tools for newspapers.
  • A. A Loop
    A Loop is a modern streetcar route in Portland, Oregon, that provides circulator service through the central city and adjacent neighborhoods as part of the Portland Streetcar system.
  • B. Blitz
    The Blitz was the sustained German bombing campaign against the United Kingdom, particularly London, during 1940–1941 in World War II.
  • C. DELTA
    DELTA is the radio callsign used by pilots and air traffic control to identify and communicate with Delta Air Lines flights.
  • D. Metro
    Metro is the rapid transit system serving the Washington, D.C. metropolitan area, operated by the Washington Metropolitan Area Transit Authority (WMATA).
  • E. ARC
    ARC is the commonly used acronym for the Augmentation Research Center, a pioneering research group known for its early work on interactive computing and human–computer interaction.
  • F. None of above. chosen

Provenance (5 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_69a247a8f6c08190bac804906d62ed5a completed Feb. 28, 2026, 1:40 a.m.
NER Named-entity recognition batch_69a24acd14b48190b80d4329621583df completed Feb. 28, 2026, 1:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69a24e6222408190bc317b90aea16849 completed Feb. 28, 2026, 2:09 a.m.
NEDg Description generation batch_69a250f6c0308190affd58f1bfa0c261 completed Feb. 28, 2026, 2:20 a.m.
NED2 Entity disambiguation (via description) batch_69a251b471688190b067c5db8f03ac47 completed Feb. 28, 2026, 2:23 a.m.
Created at: Feb. 28, 2026, 1:46 a.m.