Triple

T19664251
Position Surface form Disambiguated ID Type / Status
Subject Henry Green E472160 entity
Predicate notableWork P4 FINISHED
Object Back 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: Back | Statement: [Henry Green, notableWork, Back]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Back
Context triple: [Henry Green, notableWork, Back]
  • A. Back chosen
    Back is a small coastal village on the Isle of Lewis in Scotland’s Outer Hebrides, known for its sandy beaches and Gaelic-speaking community.
  • B. Back
    Back is a British television sitcom created by Simon Blackwell and starring David Mitchell and Robert Webb, centered on a dysfunctional family and their pub business.
  • C. BackType
    BackType was a social media analytics startup best known for creating the real-time distributed stream processing system that became Apache Storm.
  • D. Top Back
    "Top Back" is a 2006 Southern hip hop track by rapper T.I., known for its heavy bass, car-centric themes, and prominence on his album "King."
  • E. BackAgain
    BackAgain is a song featured on the album "OnMyRadio."
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6416749d48190b141a6acd20c9694 completed April 20, 2026, 3:08 p.m.
Created at: April 10, 2026, 1:45 p.m.