Triple

T766825
Position Surface form Disambiguated ID Type / Status
Subject Spanish Air Force E16192 entity
Predicate hasUnit P35 FINISHED
Object Ala 78
Ala 78 is a training wing of the Spanish Air Force specializing in helicopter pilot instruction and related aviation training.
 E97387 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: Ala 78 | Statement: [Spanish Air Force, hasUnit, Ala 78]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ala 78
Context triple: [Spanish Air Force, hasUnit, Ala 78]
  • A. Ala 31
    Ala 31 is a transport wing of the Spanish Air Force, primarily responsible for strategic and tactical airlift missions.
  • B. Ala 11
    Ala 11 is a fighter wing of the Spanish Air Force known for operating modern combat aircraft and contributing to Spain’s air defense and tactical operations.
  • C. Ala 14
    Ala 14 is a fighter wing of the Spanish Air Force known for operating advanced combat aircraft in air defense and tactical missions.
  • D. Ala 35
    Ala 35 is a transport wing of the Spanish Air Force, primarily responsible for tactical and logistical airlift missions.
  • E. Ala 48
    Ala 48 is a wing of the Spanish Air Force responsible for operating transport and support aircraft in national and international missions.
  • 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: Ala 78
Triple: [Spanish Air Force, hasUnit, Ala 78]
Generated description
Ala 78 is a training wing of the Spanish Air Force specializing in helicopter pilot instruction and related aviation training.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ala 78
Target entity description: Ala 78 is a training wing of the Spanish Air Force specializing in helicopter pilot instruction and related aviation training.
  • A. Ala 31
    Ala 31 is a transport wing of the Spanish Air Force, primarily responsible for strategic and tactical airlift missions.
  • B. Ala 11
    Ala 11 is a fighter wing of the Spanish Air Force known for operating modern combat aircraft and contributing to Spain’s air defense and tactical operations.
  • C. Ala 14
    Ala 14 is a fighter wing of the Spanish Air Force known for operating advanced combat aircraft in air defense and tactical missions.
  • D. Ala 35
    Ala 35 is a transport wing of the Spanish Air Force, primarily responsible for tactical and logistical airlift missions.
  • E. Ala 48
    Ala 48 is a wing of the Spanish Air Force responsible for operating transport and support aircraft in national and international missions.
  • 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_69a493684ee48190bd43b7c78da4aec8 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a6a0fee08190bf365d14c007e008 completed March 1, 2026, 8:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69a76d78649c8190969a3c0c2b5a8e4d completed March 3, 2026, 11:23 p.m.
NEDg Description generation batch_69a78cae18fc81908fabe38c97b71184 completed March 4, 2026, 1:36 a.m.
NED2 Entity disambiguation (via description) batch_69a78d2f349081908273db1e68b7f15e completed March 4, 2026, 1:38 a.m.
Created at: March 1, 2026, 7:37 p.m.