Triple

T19333543
Position Surface form Disambiguated ID Type / Status
Subject David Sanders E483557 entity
Predicate hasName P744 FINISHED
Object David Sanders NE NERFINISHED

How this triple was built (2 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: [David Sanders, hasName, David Sanders]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Sanders
Context triple: [David Sanders, hasName, David Sanders]
  • A. David Sanders chosen
    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.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8d13e3c81909d91d1d5ec37c095 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e61643f7b8819088a716e54a579afa completed April 20, 2026, 12:04 p.m.
Created at: April 10, 2026, 1:33 p.m.