Triple

T18362124
Position Surface form Disambiguated ID Type / Status
Subject Príncipe Island E439942 entity
Predicate IATAAirportCode P418 FINISHED
Object PCP
PCP is the IATA airport code for Príncipe Island’s main airport in São Tomé and Príncipe.
 E1320428 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: PCP | Statement: [Príncipe Island, IATAAirportCode, PCP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PCP
Context triple: [Príncipe Island, IATAAirportCode, PCP]
  • A. PCP
    PCP is the commonly used abbreviation for the Portuguese Communist Party, a major left-wing political party in Portugal.
  • B. PCP
    PCP is the former New York Stock Exchange ticker symbol for Precision Castparts Corp., a major manufacturer of complex metal components and products for aerospace, power, and industrial markets.
  • C. PCP
    PCP is the national regulatory and professional body overseeing pharmacy education and practice in Pakistan.
  • D. PCC
    PCC is a standardized, streamlined electric streetcar design widely used in North American and European cities during the mid-20th century for urban public transit.
  • E. PCC
    PCC is an international cooperative cataloging program that develops and promotes shared standards to improve the quality and efficiency of library cataloging worldwide.
  • 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: PCP
Triple: [Príncipe Island, IATAAirportCode, PCP]
Generated description
PCP is the IATA airport code for Príncipe Island’s main airport in São Tomé and Príncipe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PCP
Target entity description: PCP is the IATA airport code for Príncipe Island’s main airport in São Tomé and Príncipe.
  • A. PCP
    PCP is the former New York Stock Exchange ticker symbol for Precision Castparts Corp., a major manufacturer of complex metal components and products for aerospace, power, and industrial markets.
  • B. PCP
    PCP is the commonly used abbreviation for the Portuguese Communist Party, a major left-wing political party in Portugal.
  • C. PCP
    PCP is the national regulatory and professional body overseeing pharmacy education and practice in Pakistan.
  • D. PCC
    PCC is a standardized, streamlined electric streetcar design widely used in North American and European cities during the mid-20th century for urban public transit.
  • E. PCC
    PCC is an international cooperative cataloging program that develops and promotes shared standards to improve the quality and efficiency of library cataloging worldwide.
  • 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_69d8b918221c8190a9f7b563d64ac677 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e516dbd4748190a6c5715ef943bd4a completed April 19, 2026, 5:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03cc344eec8190873c44ab093b95e5 completed May 13, 2026, 12:56 a.m.
NEDg Description generation batch_6a03d42adeb481909b6d16ea8bdd7ed0 completed May 13, 2026, 1:30 a.m.
NED2 Entity disambiguation (via description) batch_6a03d504c0f08190b08d4bb319719643 completed May 13, 2026, 1:33 a.m.
Created at: April 10, 2026, 10:37 a.m.