Triple

T10382851
Position Surface form Disambiguated ID Type / Status
Subject Sissy Spacek E244684 entity
Predicate notableWork P4 FINISHED
Object Bloodline E514603 NE FINISHED

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: Bloodline | Statement: [Sissy Spacek, notableWork, Bloodline]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bloodline
Context triple: [Sissy Spacek, notableWork, Bloodline]
  • A. Bloodline
    Bloodline is a Star Wars novel by Claudia Gray that explores Leia Organa’s political struggles and the rise of the First Order in the years leading up to The Force Awakens.
  • B. Bloodline chosen
    Bloodline is a Netflix original drama-thriller series about a troubled Florida Keys family whose dark secrets resurface when their black sheep brother returns home.
  • C. Bloodline
    Bloodline is a work by American singer-songwriter and producer Matt Morris, likely recognized as one of his significant musical releases.
  • D. Bloodline
    Bloodline is a racing track or course associated with the Outer South region, known within that locale’s motorsport or racing circuit.
  • E. Bloodline
    "Bloodline" is a thriller novel by F. Paul Wilson, part of his long-running Repairman Jack series that blends supernatural horror with crime and conspiracy.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381b5116081908d85227bab6d3c0c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e992d8e08190aaa9a04925f52ccc completed April 7, 2026, 11:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7959b6c2c819085b606280024c0f9 completed April 9, 2026, 12:03 p.m.
Created at: April 6, 2026, 12:04 p.m.