Triple

T23063485
Position Surface form Disambiguated ID Type / Status
Subject Croydon E574969 entity
Predicate postcodeArea P920 FINISHED
Object CR
CR is the postcode area in south London and parts of Surrey that covers Croydon and its surrounding districts.
E1568025 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: CR | Statement: [Croydon, postcodeArea, CR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CR
Context triple: [Croydon, postcodeArea, CR]
  • A. CR
    CR is the designation used for a series of Italian biplane fighters designed by Fiat in the interwar period.
  • B. CR
    CR is the two-letter ISO 3166-1 alpha-2 country code representing Costa Rica.
  • C. CR
    CR was the stock ticker symbol for Conrail, a major U.S. freight railroad company formed from bankrupt Northeastern railroads and later acquired by CSX and Norfolk Southern.
  • D. CR
    CR is the commonly used abbreviation for Consumer Reports, a nonprofit organization known for its independent product testing and consumer advocacy.
  • E. CR
    CR is the vehicle registration code used on license plates for the Italian city and province of Cremona.
  • 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: CR
Triple: [Croydon, postcodeArea, CR]
Generated description
CR is the postcode area in south London and parts of Surrey that covers Croydon and its surrounding districts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CR
Target entity description: CR is the postcode area in south London and parts of Surrey that covers Croydon and its surrounding districts.
  • A. CR
    CR is a post-nominal religious title indicating membership in the Anglican religious order known as the Community of the Resurrection.
  • B. CR
    CR is the vehicle registration code used on license plates for the Italian city and province of Cremona.
  • C. CR
    CR is the two-letter ISO 3166-1 alpha-2 country code representing Costa Rica.
  • D. CR
    CR is the commonly used abbreviation for Consumer Reports, a nonprofit organization known for its independent product testing and consumer advocacy.
  • E. CR
    CR is the abbreviation for Companhia Real dos Caminhos de Ferro Portugueses, the former royal railway company that operated much of Portugal’s early rail network.
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f189a1f49c81909db7e0473ec2bb1b completed April 29, 2026, 4:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c0ae8b98881909915a157f54762d7 completed May 19, 2026, 7:02 a.m.
NEDg Description generation batch_6a0c0b7fe7848190a8e27b09748b735e completed May 19, 2026, 7:04 a.m.
NED2 Entity disambiguation (via description) batch_6a0c0bf256688190b169657a7831f6d0 completed May 19, 2026, 7:06 a.m.
Created at: April 17, 2026, 3:55 p.m.