Triple

T19920587
Position Surface form Disambiguated ID Type / Status
Subject Loeb E478783 entity
Predicate hasNotableBearer P458 FINISHED
Object David Loeb
David Loeb is a relatively obscure individual whose name is shared with several more widely known figures in fields such as finance, philanthropy, and the arts.
 E1401907 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: David Loeb | Statement: [Loeb, hasNotableBearer, David Loeb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: David Loeb
Context triple: [Loeb, hasNotableBearer, David Loeb]
  • A. David Loeb
    David Loeb is an American businessman best known as a co-founder of the major mortgage lender Countrywide Financial.
  • B. Thomas Loeb
    Thomas Loeb is known primarily as the brother of Richard Loeb, one of the infamous Leopold and Loeb criminal duo.
  • C. Benjamin Loeb
    Benjamin Loeb is a Norwegian cinematographer known for his visually distinctive work on films such as "Pieces of a Woman."
  • D. Joel Goldsmith
    Joel Goldsmith was an American composer best known for his work on film and television scores, including the Stargate franchise.
  • E. Michael D. Rosenthal
    Michael D. Rosenthal is a writer best known as the author whose work inspired the "Twilight Zone" episode "A Kind of Stopwatch."
  • 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: David Loeb
Triple: [Loeb, hasNotableBearer, David Loeb]
Generated description
David Loeb is a relatively obscure individual whose name is shared with several more widely known figures in fields such as finance, philanthropy, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: David Loeb
Target entity description: David Loeb is a relatively obscure individual whose name is shared with several more widely known figures in fields such as finance, philanthropy, and the arts.
  • A. David Loeb
    David Loeb is an American businessman best known as a co-founder of the major mortgage lender Countrywide Financial.
  • B. Thomas Loeb
    Thomas Loeb is known primarily as the brother of Richard Loeb, one of the infamous Leopold and Loeb criminal duo.
  • C. Benjamin Loeb
    Benjamin Loeb is a Norwegian cinematographer known for his visually distinctive work on films such as "Pieces of a Woman."
  • D. Joel Goldsmith
    Joel Goldsmith was an American composer best known for his work on film and television scores, including the Stargate franchise.
  • E. Michael D. Rosenthal
    Michael D. Rosenthal is a writer best known as the author whose work inspired the "Twilight Zone" episode "A Kind of Stopwatch."
  • 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e659c564788190a3893fc73fc4922b completed April 20, 2026, 4:52 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ea54913c8190be1143c1f0a11082 completed May 16, 2026, 3:53 a.m.
NEDg Description generation batch_6a07f07d33bc8190b0de5dcce7f77e7d completed May 16, 2026, 4:20 a.m.
NED2 Entity disambiguation (via description) batch_6a07f0ec7d488190991914918a3940eb completed May 16, 2026, 4:22 a.m.
Created at: April 10, 2026, 1:53 p.m.