Triple

T15977003
Position Surface form Disambiguated ID Type / Status
Subject Eskişehir Air Base E387473 entity
Predicate hasIcaoCode P419 FINISHED
Object LTBI
LTBI is the ICAO airport code assigned to Eskişehir Air Base, a military airfield in Eskişehir, Turkey.
 E1186522 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: LTBI | Statement: [Eskişehir Air Base, hasIcaoCode, LTBI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LTBI
Context triple: [Eskişehir Air Base, hasIcaoCode, LTBI]
  • A. Mycobacterium tuberculosis
    Mycobacterium tuberculosis is the pathogenic bacterial species that causes most cases of human tuberculosis, primarily affecting the lungs and spreading through airborne transmission.
  • B. Mycobacterium tuberculosis complex
    Mycobacterium tuberculosis complex is a group of closely related mycobacterial species that cause tuberculosis in humans and various animals.
  • C. BCG vaccine
    The BCG vaccine is a widely used immunization that primarily protects against severe forms of tuberculosis, especially in young children.
  • D. BCG
    BCG is a private-label sporting goods and outdoor equipment brand owned and sold exclusively by Academy Sports + Outdoors.
  • E. JRCPTB
    JRCPTB is the UK body responsible for overseeing and coordinating postgraduate training and curricula for physicians on behalf of the Royal Colleges of Physicians.
  • 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: LTBI
Triple: [Eskişehir Air Base, hasIcaoCode, LTBI]
Generated description
LTBI is the ICAO airport code assigned to Eskişehir Air Base, a military airfield in Eskişehir, Turkey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LTBI
Target entity description: LTBI is the ICAO airport code assigned to Eskişehir Air Base, a military airfield in Eskişehir, Turkey.
  • A. Mycobacterium tuberculosis
    Mycobacterium tuberculosis is the pathogenic bacterial species that causes most cases of human tuberculosis, primarily affecting the lungs and spreading through airborne transmission.
  • B. Mycobacterium tuberculosis complex
    Mycobacterium tuberculosis complex is a group of closely related mycobacterial species that cause tuberculosis in humans and various animals.
  • C. BCG vaccine
    The BCG vaccine is a widely used immunization that primarily protects against severe forms of tuberculosis, especially in young children.
  • D. BCG
    BCG is a private-label sporting goods and outdoor equipment brand owned and sold exclusively by Academy Sports + Outdoors.
  • E. JRCPTB
    JRCPTB is the UK body responsible for overseeing and coordinating postgraduate training and curricula for physicians on behalf of the Royal Colleges of Physicians.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1575166d081909c5275c235c8ce0f completed April 16, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe8e4124819084c2937f532f5ab5 completed May 9, 2026, 11:09 p.m.
NEDg Description generation batch_69ffbf1948708190975024577e58a211 completed May 9, 2026, 11:11 p.m.
NED2 Entity disambiguation (via description) batch_69ffbf745f788190abae3ba723c3a564 completed May 9, 2026, 11:12 p.m.
Created at: April 10, 2026, 4:54 a.m.