Triple

T22634228
Position Surface form Disambiguated ID Type / Status
Subject Monastir Habib Bourguiba International Airport E558635 entity
Predicate iataCode P2569 FINISHED
Object MIR
MIR is the IATA airport code for Monastir Habib Bourguiba International Airport in Monastir, Tunisia.
 E1546428 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: MIR | Statement: [Monastir Habib Bourguiba International Airport, iataCode, MIR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MIR
Context triple: [Monastir Habib Bourguiba International Airport, iataCode, MIR]
  • A. MIR
    MIR is the commonly used abbreviation for "Men in Red," typically referring to a sports team or group distinguished by their red uniforms.
  • B. MIR
    MIR is the National Rail station code for Mirfield railway station in West Yorkshire, England.
  • C. MIRI
    MIRI is the Mid-Infrared Instrument on the James Webb Space Telescope, designed to capture detailed images and spectra of celestial objects in the mid-infrared range.
  • D. MIRI
    MIRI is a research organization focused on developing the theoretical foundations needed to ensure that advanced artificial intelligence systems are safe and aligned with human values.
  • E. MI(R)
    MI(R) was a secret British military intelligence unit responsible for planning deception operations during the early years of the Second World War.
  • 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: MIR
Triple: [Monastir Habib Bourguiba International Airport, iataCode, MIR]
Generated description
MIR is the IATA airport code for Monastir Habib Bourguiba International Airport in Monastir, Tunisia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MIR
Target entity description: MIR is the IATA airport code for Monastir Habib Bourguiba International Airport in Monastir, Tunisia.
  • A. MIR
    MIR is the commonly used abbreviation for "Men in Red," typically referring to a sports team or group distinguished by their red uniforms.
  • B. MIR
    MIR is the National Rail station code for Mirfield railway station in West Yorkshire, England.
  • C. MIRI
    MIRI is the Mid-Infrared Instrument on the James Webb Space Telescope, designed to capture detailed images and spectra of celestial objects in the mid-infrared range.
  • D. MIRI
    MIRI is a research organization focused on developing the theoretical foundations needed to ensure that advanced artificial intelligence systems are safe and aligned with human values.
  • E. MI(R)
    MI(R) was a secret British military intelligence unit responsible for planning deception operations during the early years of the Second World War.
  • 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_69e245467d9881908d6985bd0db7a1f1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1700be10c8190830393fdbec1033d completed April 29, 2026, 2:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b4e0d458c8190bd53c9220952beb5 completed May 18, 2026, 5:36 p.m.
NEDg Description generation batch_6a0b4f13b2fc8190807c8dda3733cf53 completed May 18, 2026, 5:40 p.m.
NED2 Entity disambiguation (via description) batch_6a0b4fffea548190b0c3d9cce1c89aa9 completed May 18, 2026, 5:44 p.m.
Created at: April 17, 2026, 3:03 p.m.