Triple

T25353934
Position Surface form Disambiguated ID Type / Status
Subject Andrée balloon expedition 1897 E635768 entity
Predicate balloonName P158230 FINISHED
Object The Eagle
The Eagle was the hydrogen balloon used by S. A. Andrée in his ill-fated 1897 Arctic expedition attempting to reach the North Pole by air.
 E1676058 NE FINISHED

How this triple was built (3 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: The Eagle | Statement: [Andrée balloon expedition 1897, balloonName, The Eagle]
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: The Eagle
Triple: [Andrée balloon expedition 1897, balloonName, The Eagle]
Generated description
The Eagle was the hydrogen balloon used by S. A. Andrée in his ill-fated 1897 Arctic expedition attempting to reach the North Pole by air.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: balloonName
Context triple: [Andrée balloon expedition 1897, balloonName, The Eagle]
  • A. balloonName chosen
    Indicates that a balloon is identified or labeled by a specific name.
  • B. balloonType
    Indicates the specific kind or category of balloon associated with an entity.
  • C. typicalNumberOfBalloons
    Indicates the usual or expected quantity of balloons associated with something in a given context.
  • D. balloonMaterial
    Indicates that one entity is made of, or composed from, the material specified by the other entity.
  • E. ballName
    Indicates that an entity has a specific name assigned to a ball.
  • F. None of above.

Provenance (6 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_69e75a9ac5d881909387ed766e20cd47 completed April 21, 2026, 11:08 a.m.
NER Named-entity recognition batch_69f49dfedae88190a02f10196ef45ffa completed May 1, 2026, 12:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1075fd4c0081908b40904f881ea3b6 completed May 22, 2026, 3:27 p.m.
NEDg Description generation batch_6a1076b9b58881908eb0b619471c3879 completed May 22, 2026, 3:31 p.m.
NED2 Entity disambiguation (via description) batch_6a1077d01fa08190b5439eba879538ef completed May 22, 2026, 3:35 p.m.
PD Predicate disambiguation batch_69f4683b34748190818428489a226124 completed May 1, 2026, 8:45 a.m.
Created at: April 21, 2026, 1:34 p.m.