Triple

T9046103
Position Surface form Disambiguated ID Type / Status
Subject The Sacrifice E216758 entity
Predicate productionCompany P490 FINISHED
Object Sandrews
Sandrews was a prominent Swedish film production and distribution company active during much of the 20th century.
 E774340 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: Sandrews | Statement: [The Sacrifice, productionCompany, Sandrews]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sandrews
Context triple: [The Sacrifice, productionCompany, Sandrews]
  • A. McElderry
    McElderry is the surname of Margaret K. McElderry, a pioneering American children's book editor and publisher.
  • B. Sandys
    Sandys is the surname of Frederic Sandys, a 19th-century British painter and illustrator associated with the Pre-Raphaelite movement.
  • C. Rowlands
    Rowlands is the surname of June Rowlands, a notable Canadian politician and the first female mayor of Toronto.
  • D. Damsay
    Damsay is a small uninhabited island in the Orkney archipelago of Scotland, known for its low-lying terrain and archaeological remains.
  • E. Lundie
    Lundie is a small rural settlement in Angus, Scotland, situated near the Sidlaw Hills and known for its scenic countryside setting.
  • 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: Sandrews
Triple: [The Sacrifice, productionCompany, Sandrews]
Generated description
Sandrews was a prominent Swedish film production and distribution company active during much of the 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sandrews
Target entity description: Sandrews was a prominent Swedish film production and distribution company active during much of the 20th century.
  • A. McElderry
    McElderry is the surname of Margaret K. McElderry, a pioneering American children's book editor and publisher.
  • B. Sandys
    Sandys is the surname of Frederic Sandys, a 19th-century British painter and illustrator associated with the Pre-Raphaelite movement.
  • C. Rowlands
    Rowlands is the surname of June Rowlands, a notable Canadian politician and the first female mayor of Toronto.
  • D. Damsay
    Damsay is a small uninhabited island in the Orkney archipelago of Scotland, known for its low-lying terrain and archaeological remains.
  • E. Lundie
    Lundie is a small rural settlement in Angus, Scotland, situated near the Sidlaw Hills and known for its scenic countryside setting.
  • 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_69ca83d22d488190adbce5e020e9cd1d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6b4e4b888190a425e29b193b506f completed April 1, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfebb7f668819099125ab727cd50b1 completed April 3, 2026, 4:32 p.m.
NEDg Description generation batch_69cfed8970448190b3deac1d8f46c639 completed April 3, 2026, 4:40 p.m.
NED2 Entity disambiguation (via description) batch_69cfedf299908190852cc627fd7134b9 completed April 3, 2026, 4:42 p.m.
Created at: March 30, 2026, 7:09 p.m.