Triple

T2860618
Position Surface form Disambiguated ID Type / Status
Subject Albert Lasker E63309 entity
Predicate employer P7 FINISHED
Object Lord & Thomas
Lord & Thomas was a prominent early 20th-century American advertising agency known for pioneering modern advertising techniques.
 E305495 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: Lord & Thomas | Statement: [Albert Lasker, employer, Lord & Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lord & Thomas
Context triple: [Albert Lasker, employer, Lord & Thomas]
  • A. Pavia & Harcourt
    Pavia & Harcourt is a New York–based law firm known in part for employing future U.S. Supreme Court Justice Sonia Sotomayor early in her legal career.
  • B. Penge and Cator
    Penge and Cator is an electoral ward in the London Borough of Bromley, covering the Penge area and parts of nearby Cator.
  • C. Scott & Linton
    Scott & Linton was a 19th-century Scottish shipbuilding firm best known for constructing the famous tea clipper Cutty Sark.
  • D. Lord Hodge
    Lord Hodge is a senior Scottish jurist who serves as Deputy President of the Supreme Court of the United Kingdom.
  • E. Sir Thomas Bornwell
    Sir Thomas Bornwell is a central character in James Shirley’s Caroline-era comedy "The Lady of Pleasure," representing the moral and social tensions of the English aristocracy.
  • 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: Lord & Thomas
Triple: [Albert Lasker, employer, Lord & Thomas]
Generated description
Lord & Thomas was a prominent early 20th-century American advertising agency known for pioneering modern advertising techniques.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lord & Thomas
Target entity description: Lord & Thomas was a prominent early 20th-century American advertising agency known for pioneering modern advertising techniques.
  • A. Pavia & Harcourt
    Pavia & Harcourt is a New York–based law firm known in part for employing future U.S. Supreme Court Justice Sonia Sotomayor early in her legal career.
  • B. Penge and Cator
    Penge and Cator is an electoral ward in the London Borough of Bromley, covering the Penge area and parts of nearby Cator.
  • C. Scott & Linton
    Scott & Linton was a 19th-century Scottish shipbuilding firm best known for constructing the famous tea clipper Cutty Sark.
  • D. Lord Hodge
    Lord Hodge is a senior Scottish jurist who serves as Deputy President of the Supreme Court of the United Kingdom.
  • E. Sir Thomas Bornwell
    Sir Thomas Bornwell is a central character in James Shirley’s Caroline-era comedy "The Lady of Pleasure," representing the moral and social tensions of the English aristocracy.
  • 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_69ab4c41e8c08190a9e8f5249cc12610 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdf8c676c8190ab29f89d50bd09c3 completed March 7, 2026, 8:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01d9b820c8190991bae0e936eed9c completed March 10, 2026, 1:33 p.m.
NEDg Description generation batch_69b020568f348190b9c603c21c65187d completed March 10, 2026, 1:44 p.m.
NED2 Entity disambiguation (via description) batch_69b020da12b08190851caee1996a76eb completed March 10, 2026, 1:47 p.m.
Created at: March 6, 2026, 10:02 p.m.