Triple

T4443752
Position Surface form Disambiguated ID Type / Status
Subject Erlang E96230 entity
Predicate designedBy P184 FINISHED
Object Mike Williams
Mike Williams is a Swedish computer scientist best known as one of the creators of the Erlang programming language.
E442480 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: Mike Williams | Statement: [Erlang, designedBy, Mike Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Williams
Context triple: [Erlang, designedBy, Mike Williams]
  • A. Jason Williams
    Jason Williams is a former American NBA point guard known for his flashy playmaking and crowd-pleasing style, particularly during his time with the Sacramento Kings.
  • B. Jason Williams
    Jason Williams is the brother of American actress Michelle Williams.
  • C. Rodney Williams
    Rodney Williams is an Antiguan politician and medical doctor who has served as the Governor-General of Antigua and Barbuda.
  • D. Brian Douglas Williams
    Brian Douglas Williams is an American television journalist best known for anchoring NBC Nightly News and later hosting "The 11th Hour" on MSNBC.
  • E. Mancel Warrick
    Mancel Warrick was the father of American soul and R&B singer Dee Dee Warwick and a member of the musical Warwick family.
  • 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: Mike Williams
Triple: [Erlang, designedBy, Mike Williams]
Generated description
Mike Williams is a Swedish computer scientist best known as one of the creators of the Erlang programming language.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mike Williams
Target entity description: Mike Williams is a Swedish computer scientist best known as one of the creators of the Erlang programming language.
  • A. Jason Williams
    Jason Williams is a former American NBA point guard known for his flashy playmaking and crowd-pleasing style, particularly during his time with the Sacramento Kings.
  • B. Jason Williams
    Jason Williams is the brother of American actress Michelle Williams.
  • C. Rodney Williams
    Rodney Williams is an Antiguan politician and medical doctor who has served as the Governor-General of Antigua and Barbuda.
  • D. Brian Douglas Williams
    Brian Douglas Williams is an American television journalist best known for anchoring NBC Nightly News and later hosting "The 11th Hour" on MSNBC.
  • E. Mancel Warrick
    Mancel Warrick was the father of American soul and R&B singer Dee Dee Warwick and a member of the musical Warwick family.
  • 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_69b345415ba481908df738e7174448ba completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b355b052688190a0d8e5912f82151c completed March 13, 2026, 12:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69b62818295481909c0ffa377570effc completed March 15, 2026, 3:31 a.m.
NEDg Description generation batch_69b628ffed1c819097d048712e9aafef completed March 15, 2026, 3:35 a.m.
NED2 Entity disambiguation (via description) batch_69b6298d1ff88190a58a6fc5992ef864 completed March 15, 2026, 3:37 a.m.
Created at: March 12, 2026, 11:32 p.m.