Triple

T10914097
Position Surface form Disambiguated ID Type / Status
Subject Saker falcon E257775 entity
Predicate commonName P570 FINISHED
Object Saker
Saker is a large, powerful falcon species native to Eurasia, known for its speed, hunting prowess, and use in traditional falconry.
 E894259 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: Saker | Statement: [Saker falcon, commonName, Saker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Saker
Context triple: [Saker falcon, commonName, Saker]
  • A. Sako
    Sako is a Finnish firearms manufacturer renowned for its high-quality rifles and precision engineering, operating as a subsidiary of Beretta.
  • B. Raptor
    Raptor is the NATO reporting name for the F-22, a fifth-generation American stealth air superiority fighter aircraft.
  • C. Raptor
    Raptor is a steel inverted roller coaster at Cedar Point known for its intense inversions and high-speed, suspended-track design.
  • D. Raptor
    Raptor is SpaceX’s next-generation methane-fueled rocket engine designed to power the company’s Starship launch system with high efficiency and reusability.
  • E. Sokół
    Sokół is a Polish rapper, songwriter, and music producer known as one of the most influential figures in Poland’s hip-hop scene.
  • 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: Saker
Triple: [Saker falcon, commonName, Saker]
Generated description
Saker is a large, powerful falcon species native to Eurasia, known for its speed, hunting prowess, and use in traditional falconry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Saker
Target entity description: Saker is a large, powerful falcon species native to Eurasia, known for its speed, hunting prowess, and use in traditional falconry.
  • A. Sako
    Sako is a Finnish firearms manufacturer renowned for its high-quality rifles and precision engineering, operating as a subsidiary of Beretta.
  • B. Raptor
    Raptor is a steel inverted roller coaster at Cedar Point known for its intense inversions and high-speed, suspended-track design.
  • C. Raptor
    Raptor is the NATO reporting name for the F-22, a fifth-generation American stealth air superiority fighter aircraft.
  • D. Raptor
    Raptor is SpaceX’s next-generation methane-fueled rocket engine designed to power the company’s Starship launch system with high efficiency and reusability.
  • E. Sokół
    Sokół is a Polish rapper, songwriter, and music producer known as one of the most influential figures in Poland’s hip-hop scene.
  • 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_69d6aa864ed88190818280ab6791d065 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d77073d12881908ea59771b84bc804 completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e216eb77dc81908c380f5fcd507275 completed April 17, 2026, 11:18 a.m.
NEDg Description generation batch_69e21d8952c881908a952de83754e049 completed April 17, 2026, 11:46 a.m.
NED2 Entity disambiguation (via description) batch_69e2247fbd348190bb0d221923dac892 completed April 17, 2026, 12:16 p.m.
Created at: April 8, 2026, 9:22 p.m.