Triple

T19241447
Position Surface form Disambiguated ID Type / Status
Subject Abu Simbel Airport E481141 entity
Predicate ICAOcode P419 FINISHED
Object HEBL
HEBL is the ICAO airport code for Abu Simbel Airport, which serves the area near the Abu Simbel temples in southern Egypt.
E1365405 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: HEBL | Statement: [Abu Simbel Airport, ICAOcode, HEBL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HEBL
Context triple: [Abu Simbel Airport, ICAOcode, HEBL]
  • A. HEL
    HEL is the three-letter IATA airport code for Helsinki Airport, the main international gateway to Finland’s capital region.
  • B. HBL
    HBL (Habib Bank Limited) is one of Pakistan’s largest and oldest commercial banks, widely recognized for its extensive branch network and major corporate sponsorships, including in sports.
  • C. HBE
    HBE is the IATA airport code for Borg El Arab Airport, the main international airport serving Alexandria, Egypt.
  • D. HEBA
    HEBA is the ICAO airport code for Borg El Arab Airport, the main international airport serving Alexandria, Egypt.
  • E. HE
    HE is the Faculty of Health at Aarhus University, responsible for education and research in medical and health sciences.
  • 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: HEBL
Triple: [Abu Simbel Airport, ICAOcode, HEBL]
Generated description
HEBL is the ICAO airport code for Abu Simbel Airport, which serves the area near the Abu Simbel temples in southern Egypt.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: HEBL
Target entity description: HEBL is the ICAO airport code for Abu Simbel Airport, which serves the area near the Abu Simbel temples in southern Egypt.
  • A. HEL
    HEL is the three-letter IATA airport code for Helsinki Airport, the main international gateway to Finland’s capital region.
  • B. HBL
    HBL (Habib Bank Limited) is one of Pakistan’s largest and oldest commercial banks, widely recognized for its extensive branch network and major corporate sponsorships, including in sports.
  • C. HBE
    HBE is the IATA airport code for Borg El Arab Airport, the main international airport serving Alexandria, Egypt.
  • D. HEBA
    HEBA is the ICAO airport code for Borg El Arab Airport, the main international airport serving Alexandria, Egypt.
  • E. HE
    HE is the Faculty of Health at Aarhus University, responsible for education and research in medical and health sciences.
  • 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5faf14564819085009adf822804ab completed April 20, 2026, 10:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0705dc40f08190a9c4d48455343a42 completed May 15, 2026, 11:39 a.m.
NEDg Description generation batch_6a070651263c8190b33b74f3dfd4a515 completed May 15, 2026, 11:41 a.m.
NED2 Entity disambiguation (via description) batch_6a0706ca714c8190baf78f8fa0e5f002 completed May 15, 2026, 11:43 a.m.
Created at: April 10, 2026, 1:26 p.m.