Triple

T21612110
Position Surface form Disambiguated ID Type / Status
Subject Legazpi E533337 entity
Predicate hasStationCode P1289 FINISHED
Object LZP
LZP is the station code for Legazpi railway station in the Philippines.
 E1493407 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: LZP | Statement: [Legazpi, hasStationCode, LZP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LZP
Context triple: [Legazpi, hasStationCode, LZP]
  • A. LZA
    LZA is the regional vehicle registration code assigned to motor vehicles registered in the city of Zamość in Poland.
  • B. LZIB
    LZIB is the ICAO airport code for M. R. Štefánik Airport, the main international airport serving Bratislava, Slovakia.
  • C. LZ 4
    LZ 4 was an early experimental German rigid airship built by Count Zeppelin that became famous after its 1908 crash and fire, which nonetheless spurred public support for further airship development.
  • D. LZH
    LZH is the IATA airport code for Liuzhou Bailian Airport, a commercial airport serving Liuzhou in Guangxi, China.
  • E. LZ
    LZ is the vehicle registration code assigned to the municipality of Kals am Großglockner in Austria.
  • 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: LZP
Triple: [Legazpi, hasStationCode, LZP]
Generated description
LZP is the station code for Legazpi railway station in the Philippines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LZP
Target entity description: LZP is the station code for Legazpi railway station in the Philippines.
  • A. LZA
    LZA is the regional vehicle registration code assigned to motor vehicles registered in the city of Zamość in Poland.
  • B. LZIB
    LZIB is the ICAO airport code for M. R. Štefánik Airport, the main international airport serving Bratislava, Slovakia.
  • C. LZ 4
    LZ 4 was an early experimental German rigid airship built by Count Zeppelin that became famous after its 1908 crash and fire, which nonetheless spurred public support for further airship development.
  • D. LZH
    LZH is the IATA airport code for Liuzhou Bailian Airport, a commercial airport serving Liuzhou in Guangxi, China.
  • E. LZ
    LZ is the stock ticker symbol for The Lubrizol Corporation, a specialty chemicals company known for its lubricant additives and advanced materials.
  • 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_69e0c46411108190bba0d4176dffc9f3 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef3ba79424819094e9ee93c4bbcc0b completed April 27, 2026, 10:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09fd3d0d9881909d04a901cf65c211 completed May 17, 2026, 5:39 p.m.
NEDg Description generation batch_6a0a0c1bb6188190966c2db0f61048f7 completed May 17, 2026, 6:42 p.m.
NED2 Entity disambiguation (via description) batch_6a0a0cb1b9d08190aa0edccd5a49b289 completed May 17, 2026, 6:45 p.m.
Created at: April 16, 2026, 6:33 p.m.