Triple

T13639784
Position Surface form Disambiguated ID Type / Status
Subject Labour and Welfare Bureau E325942 entity
Predicate hasAbbreviation P43 FINISHED
Object LWB
LWB is the official abbreviation for Hong Kong’s Labour and Welfare Bureau, the government body responsible for labour policy and social welfare matters.
 E1052574 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: LWB | Statement: [Labour and Welfare Bureau, hasAbbreviation, LWB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LWB
Context triple: [Labour and Welfare Bureau, hasAbbreviation, LWB]
  • A. LW
    LW is the station code used to identify Lawrence West station on Toronto's subway system.
  • B. WB
    WB is a major film and entertainment studio best known for producing and distributing movies, television shows, and other media worldwide.
  • C. WB
    WB is the official vehicle registration code used for motor vehicles registered in the Indian state of West Bengal.
  • D. WRB
    WRB is the acronym for the War Refugee Board, a U.S. government agency established during World War II to aid civilian victims of the Nazis.
  • E. WRB
    WRB is the IATA airport code for Robins Air Force Base in Georgia, United States.
  • 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: LWB
Triple: [Labour and Welfare Bureau, hasAbbreviation, LWB]
Generated description
LWB is the official abbreviation for Hong Kong’s Labour and Welfare Bureau, the government body responsible for labour policy and social welfare matters.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LWB
Target entity description: LWB is the official abbreviation for Hong Kong’s Labour and Welfare Bureau, the government body responsible for labour policy and social welfare matters.
  • A. LW
    LW is the station code used to identify Lawrence West station on Toronto's subway system.
  • B. WB
    WB is a major film and entertainment studio best known for producing and distributing movies, television shows, and other media worldwide.
  • C. WB
    WB is the official vehicle registration code used for motor vehicles registered in the Indian state of West Bengal.
  • D. WRB
    WRB is the acronym for the War Refugee Board, a U.S. government agency established during World War II to aid civilian victims of the Nazis.
  • E. WRB
    WRB is the IATA airport code for Robins Air Force Base in Georgia, United States.
  • 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_69d8076beddc8190a53156f5bea77f5e completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc5aac7308190a3fd26baeade8f2a completed April 12, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78af46fe481909c6f9a6f58f887d1 completed May 3, 2026, 5:50 p.m.
NEDg Description generation batch_69f78bd316788190a245e8199f6ac87b completed May 3, 2026, 5:54 p.m.
NED2 Entity disambiguation (via description) batch_69f78c94da6c8190b9bc1d04cee19c3c completed May 3, 2026, 5:57 p.m.
Created at: April 9, 2026, 9:51 p.m.