Triple

T15698420
Position Surface form Disambiguated ID Type / Status
Subject Flowing Gold E380526 entity
Predicate title P38 FINISHED
Object Flowing Gold E380526 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: Flowing Gold | Statement: [Flowing Gold, title, Flowing Gold]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Flowing Gold
Context triple: [Flowing Gold, title, Flowing Gold]
  • A. Flowing Gold chosen
    "Flowing Gold" is a 1940 adventure drama film starring Frances Farmer, based on Rex Beach’s novel about intrigue and danger in the Texas oil fields.
  • B. Cream of Gold
    "Cream of Gold" is a song by the American indie rock band Pavement from their 1999 album Terror Twilight.
  • C. Gold Dust
    "Gold Dust" is a 2012 studio album by Tori Amos featuring orchestral re-recordings of songs from across her career.
  • D. House of gold
    House of gold is a Marian title from the Litany of Loreto that poetically honors the Virgin Mary as a precious, holy dwelling place of God.
  • E. The Glitter and the Gold
    The Glitter and the Gold is the memoir of American heiress Consuelo Vanderbilt, recounting her life as a Gilded Age socialite and Duchess of Marlborough.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f6c3328819081325b702ca92862 completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff7571f1888190b83af75ec9c7432b completed May 9, 2026, 5:57 p.m.
Created at: April 10, 2026, 4:44 a.m.