Triple

T6469341
Position Surface form Disambiguated ID Type / Status
Subject Banque du Liban E142308 entity
Predicate shortName P43 FINISHED
Object BDL
BDL is the commonly used abbreviation for Banque du Liban, the central bank of Lebanon responsible for the country’s monetary policy and financial stability.
 E594250 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: BDL | Statement: [Banque du Liban, shortName, BDL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BDL
Context triple: [Banque du Liban, shortName, BDL]
  • A. BDL
    BDL is the three-letter IATA airport code for Bradley International Airport, a major commercial airport serving the Hartford–Springfield region in the northeastern United States.
  • B. BD
    BD is the currency symbol used to denote the Bahraini dinar, the official monetary unit of Bahrain.
  • C. BD
    BD is the UK postcode area covering Bradford and surrounding parts of West Yorkshire.
  • D. BD
    BD is the station code used to identify Bandung railway station in Indonesia’s rail network.
  • E. LBT
    LBT is the public-facing brand name and logo used by Long Beach Transit, the primary public transportation agency serving Long Beach, California, and surrounding areas.
  • 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: BDL
Triple: [Banque du Liban, shortName, BDL]
Generated description
BDL is the commonly used abbreviation for Banque du Liban, the central bank of Lebanon responsible for the country’s monetary policy and financial stability.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BDL
Target entity description: BDL is the commonly used abbreviation for Banque du Liban, the central bank of Lebanon responsible for the country’s monetary policy and financial stability.
  • A. BDL
    BDL is the three-letter IATA airport code for Bradley International Airport, a major commercial airport serving the Hartford–Springfield region in the northeastern United States.
  • B. BD
    BD is the currency symbol used to denote the Bahraini dinar, the official monetary unit of Bahrain.
  • C. BD
    BD is the UK postcode area covering Bradford and surrounding parts of West Yorkshire.
  • D. BD
    BD is the station code used to identify Bandung railway station in Indonesia’s rail network.
  • E. LBT
    LBT is the public-facing brand name and logo used by Long Beach Transit, the primary public transportation agency serving Long Beach, California, and surrounding areas.
  • 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_69c008d3bf4c8190bcf798c5ba9d6fb3 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06a16272c81909313455002cd884d completed March 22, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64beed2488190952c0b60261df85e completed March 27, 2026, 9:20 a.m.
NEDg Description generation batch_69c64cd369048190bc0702592083a909 completed March 27, 2026, 9:24 a.m.
NED2 Entity disambiguation (via description) batch_69c64d911a1881908b280636365a4858 completed March 27, 2026, 9:27 a.m.
Created at: March 22, 2026, 4:50 p.m.