Triple

T21123262
Position Surface form Disambiguated ID Type / Status
Subject Unifeeder E520485 entity
Predicate hasSubsidiary P254 FINISHED
Object Unifeeder Feeder 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: Unifeeder Feeder | Statement: [Unifeeder, hasSubsidiary, Unifeeder Feeder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Unifeeder Feeder
Context triple: [Unifeeder, hasSubsidiary, Unifeeder Feeder]
  • A. Unifeeder chosen
    Unifeeder is a European logistics and shortsea shipping company that operates container feeder and regional transport services connecting major ports and smaller terminals.
  • B. Feeders and Eaters
    "Feeders and Eaters" is a dark, unsettling horror short story by Neil Gaiman that explores themes of hunger, obsession, and the grotesque through a disturbing encounter between old acquaintances.
  • C. Fryer
    Fryer is the middle name of William Fryer Harvey, an English writer best known for his classic horror and ghost stories.
  • D. Feed the Machine
    Feed the Machine is a hard rock studio album by Canadian band Nickelback, noted for its heavier sound and socially charged themes.
  • E. Meco
    Meco is a municipality in central Spain’s Community of Madrid, known for its location in the Henares Corridor near Alcalá de Henares.
  • 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_69e0b50a623881909c0bbaf4f2c055e7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72236b2d88190bef9f0cd6924ca92 completed April 21, 2026, 7:07 a.m.
Created at: April 16, 2026, 2:55 p.m.