Triple

T1611090
Position Surface form Disambiguated ID Type / Status
Subject Tom Preston-Werner E34614 entity
Predicate coFounded P104 FINISHED
Object Gravatar
Gravatar is an online service that provides globally recognized avatars linked to users’ email addresses for use across websites and applications.
E120447 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: Gravatar | Statement: [Tom Preston-Werner, coFounded, Gravatar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gravatar
Context triple: [Tom Preston-Werner, coFounded, Gravatar]
  • A. Griff
    Griff is the lion mascot of the Grand Rapids Griffins, a professional ice hockey team in the American Hockey League.
  • B. Graf
    Graf is a historical German noble title roughly equivalent to a count in other European aristocratic systems.
  • C. Garth
    Garth is a fictional character from the American prime-time television soap opera "Falcon Crest."
  • D. Grok
    Grok is an AI chatbot developed by xAI, designed to provide conversational access to real-time information and reasoning capabilities.
  • E. Garthdee
    Garthdee is a riverside area in the southwest of Aberdeen, Scotland, known for hosting the main campus of Robert Gordon University.
  • 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: Gravatar
Triple: [Tom Preston-Werner, coFounded, Gravatar]
Generated description
Gravatar is an online service that provides globally recognized avatars linked to users’ email addresses for use across websites and applications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gravatar
Target entity description: Gravatar is an online service that provides globally recognized avatars linked to users’ email addresses for use across websites and applications.
  • A. Gravatar chosen
    Gravatar is an online service that provides globally recognized avatars linked to users’ email addresses for use across websites and applications.
  • B. Griff
    Griff is the lion mascot of the Grand Rapids Griffins, a professional ice hockey team in the American Hockey League.
  • C. Graf
    Graf is a historical German noble title roughly equivalent to a count in other European aristocratic systems.
  • D. Garth
    Garth is a fictional character from the American prime-time television soap opera "Falcon Crest."
  • E. Grok
    Grok is an AI chatbot developed by xAI, designed to provide conversational access to real-time information and reasoning capabilities.
  • F. None of above.

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_69a885ffc5ec819091afa325d5f9611c completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa622b9fbc8190bff82acdde10deb6 completed March 6, 2026, 5:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad51c751308190a89f6462ee365418 completed March 8, 2026, 10:39 a.m.
NEDg Description generation batch_69ad52f6b15c819097d4e56884e31600 completed March 8, 2026, 10:44 a.m.
NED2 Entity disambiguation (via description) batch_69ad53536a108190b97b7017ad567ad5 completed March 8, 2026, 10:45 a.m.
Created at: March 4, 2026, 7:28 p.m.