Triple

T3799725
Position Surface form Disambiguated ID Type / Status
Subject Zaragoza Air Base E91658 entity
Predicate ICAOCode P419 FINISHED
Object LEZG
LEZG is the ICAO airport code assigned to Zaragoza Air Base in Spain.
E388992 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: LEZG | Statement: [Zaragoza Air Base, ICAOCode, LEZG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LEZG
Context triple: [Zaragoza Air Base, ICAOCode, LEZG]
  • A. Lezginka
    Lezginka is a fast-paced, energetic folk dance of the Caucasus region, characterized by sharp, agile movements and often performed at celebrations and cultural events.
  • B. LEZL
    LEZL is the ICAO airport code for Seville Airport, a major international airport serving the city of Seville in southern Spain.
  • C. Lezgian
    Lezgian is a Northeast Caucasian language spoken primarily by the Lezgin people in southern Dagestan and northern Azerbaijan.
  • D. Seraiki
    Seraiki is an Indo-Aryan language spoken primarily in central and southern Pakistan, especially in the southern Punjab region.
  • E. Lezginka (Azerbaijani variant)
    Lezginka (Azerbaijani variant) is a fast-paced, energetic Caucasian folk dance in Azerbaijan characterized by sharp, expressive movements and often performed at celebrations and cultural events.
  • 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: LEZG
Triple: [Zaragoza Air Base, ICAOCode, LEZG]
Generated description
LEZG is the ICAO airport code assigned to Zaragoza Air Base in Spain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LEZG
Target entity description: LEZG is the ICAO airport code assigned to Zaragoza Air Base in Spain.
  • A. Lezginka
    Lezginka is a fast-paced, energetic folk dance of the Caucasus region, characterized by sharp, agile movements and often performed at celebrations and cultural events.
  • B. LEZL
    LEZL is the ICAO airport code for Seville Airport, a major international airport serving the city of Seville in southern Spain.
  • C. Lezgian
    Lezgian is a Northeast Caucasian language spoken primarily by the Lezgin people in southern Dagestan and northern Azerbaijan.
  • D. Seraiki
    Seraiki is an Indo-Aryan language spoken primarily in central and southern Pakistan, especially in the southern Punjab region.
  • E. Lezginka (Azerbaijani variant)
    Lezginka (Azerbaijani variant) is a fast-paced, energetic Caucasian folk dance in Azerbaijan characterized by sharp, expressive movements and often performed at celebrations and cultural events.
  • 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_69aed96354f48190a768966d6bd19b04 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee7a43c408190a54cff649f63e69f completed March 9, 2026, 3:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4f064471881908b52b2f64e50a83d completed March 14, 2026, 5:21 a.m.
NEDg Description generation batch_69b4f1fae7ac8190909b05c0d685e377 completed March 14, 2026, 5:28 a.m.
NED2 Entity disambiguation (via description) batch_69b4f29e5fb48190982ab2844eb8c179 completed March 14, 2026, 5:31 a.m.
Created at: March 9, 2026, 3:15 p.m.