Triple

T21335312
Position Surface form Disambiguated ID Type / Status
Subject Gail Berke E526028 entity
Predicate romanticPartner P9994 FINISHED
Object David Sanders
David Sanders is an individual known primarily for his romantic relationship with Gail Berke.
E1478325 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 Sanders | Statement: [Gail Berke, romanticPartner, David Sanders]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Sanders
Context triple: [Gail Berke, romanticPartner, David Sanders]
  • A. David Sanders
    David Sanders is the protagonist of the thriller novel "The Deep," around whom the story’s central mystery and underwater adventure revolve.
  • B. Thomas Sanders
    Thomas Sanders was an American businessman and early telecommunications pioneer who co-founded the company that became AT&T.
  • C. Mark Sandler
    Mark Sandler is a computer scientist and machine learning researcher known for his work on efficient deep neural network architectures, including the development of MobileNetV2.
  • D. Barry Sandler
    Barry Sandler is an American screenwriter and producer best known for his work on films such as "Making Love" and various adaptations and thrillers in the 1970s and 1980s.
  • E. Marty Sanders
    Marty Sanders is an American guitarist and singer best known as a longtime member of the 1960s pop-rock group Jay and the Americans.
  • 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 Sanders
Triple: [Gail Berke, romanticPartner, David Sanders]
Generated description
David Sanders is an individual known primarily for his romantic relationship with Gail Berke.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Sanders
Target entity description: David Sanders is an individual known primarily for his romantic relationship with Gail Berke.
  • A. David Sanders
    David Sanders is the protagonist of the thriller novel "The Deep," around whom the story’s central mystery and underwater adventure revolve.
  • B. Thomas Sanders
    Thomas Sanders was an American businessman and early telecommunications pioneer who co-founded the company that became AT&T.
  • C. Mark Sandler
    Mark Sandler is a computer scientist and machine learning researcher known for his work on efficient deep neural network architectures, including the development of MobileNetV2.
  • D. Barry Sandler
    Barry Sandler is an American screenwriter and producer best known for his work on films such as "Making Love" and various adaptations and thrillers in the 1970s and 1980s.
  • E. Marty Sanders
    Marty Sanders is an American guitarist and singer best known as a longtime member of the 1960s pop-rock group Jay and the Americans.
  • 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_69e0b51c33048190ab27cede74ef798c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e898d6fcbc8190b83d9cfc9b4ca123 completed April 22, 2026, 9:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09a5c07438819084e08576a703406c completed May 17, 2026, 11:25 a.m.
NEDg Description generation batch_6a09a6723714819087d80d62bdcb3926 completed May 17, 2026, 11:28 a.m.
NED2 Entity disambiguation (via description) batch_6a09a6d55bf08190bb4a90fbb258f49b completed May 17, 2026, 11:30 a.m.
Created at: April 16, 2026, 4:43 p.m.