Triple

T828972
Position Surface form Disambiguated ID Type / Status
Subject Tunisair E17920 entity
Predicate ICAOcode P419 FINISHED
Object TAR
TAR is the ICAO airline designator assigned to Tunisair, the national flag carrier of Tunisia.
 E96505 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: TAR | Statement: [Tunisair, ICAOcode, TAR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TAR
Context triple: [Tunisair, ICAOcode, TAR]
  • A. ATA
    ATA (Advanced Technology Attachment), commonly known as IDE, is a standard interface used to connect storage devices like hard drives and optical drives to a computer's motherboard.
  • B. GNU Tar
    GNU Tar is a widely used free software utility for creating, maintaining, modifying, and extracting files from archive files, especially on Unix-like systems.
  • C. TPA
    TPA is an abbreviation commonly used for a Tri-Party Agreement, a legal contract involving three separate parties that defines their respective rights and obligations.
  • D. TB
    TB is the standard abbreviation for the Tampa Bay Rays, a Major League Baseball team based in St. Petersburg, Florida.
  • E. Tarifit
    Tarifit is a Northern Berber language spoken primarily by the Riffian people in the Rif region of northern Morocco.
  • 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: TAR
Triple: [Tunisair, ICAOcode, TAR]
Generated description
TAR is the ICAO airline designator assigned to Tunisair, the national flag carrier of Tunisia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TAR
Target entity description: TAR is the ICAO airline designator assigned to Tunisair, the national flag carrier of Tunisia.
  • A. ATA
    ATA (Advanced Technology Attachment), commonly known as IDE, is a standard interface used to connect storage devices like hard drives and optical drives to a computer's motherboard.
  • B. GNU Tar
    GNU Tar is a widely used free software utility for creating, maintaining, modifying, and extracting files from archive files, especially on Unix-like systems.
  • C. TPA
    TPA is an abbreviation commonly used for a Tri-Party Agreement, a legal contract involving three separate parties that defines their respective rights and obligations.
  • D. TB
    TB is the standard abbreviation for the Tampa Bay Rays, a Major League Baseball team based in St. Petersburg, Florida.
  • E. Tarifit
    Tarifit is a Northern Berber language spoken primarily by the Riffian people in the Rif region of northern Morocco.
  • 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_69a4937c9c188190aaa216f6b466f452 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ab9b458881909aa23f0eb7cbc87f completed March 1, 2026, 9:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a76d97a3b08190b7a5c635d74bcd47 completed March 3, 2026, 11:24 p.m.
NEDg Description generation batch_69a783814b188190b449cd191667f1a1 completed March 4, 2026, 12:57 a.m.
NED2 Entity disambiguation (via description) batch_69a7840593988190b6882b456f0eea41 completed March 4, 2026, 12:59 a.m.
Created at: March 1, 2026, 7:38 p.m.