Triple

T15026594
Position Surface form Disambiguated ID Type / Status
Subject Columbia Airport E378231 entity
Predicate faaCode P420 FINISHED
Object O22
O22 is the Federal Aviation Administration location identifier assigned to Columbia Airport in the United States.
 E1133101 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: O22 | Statement: [Columbia Airport, faaCode, O22]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: O22
Context triple: [Columbia Airport, faaCode, O22]
  • A. N222
    N222 is a regional road in the Netherlands that connects the town of Wateringen with surrounding areas in the Westland region.
  • B. E22
    E22 is a major European route that forms part of the international E-road network, linking multiple countries across Europe.
  • C. D22
    D22 is the second-generation Nissan Navara (also known as the Nissan Frontier in some markets), a compact pickup truck platform produced from the late 1990s into the 2000s.
  • D. N228
    N228 is a regional road in the Netherlands that provides access to and from the village of Benschop.
  • E. G22
    G22 is BMW’s internal model designation for the second-generation 4 Series coupe, introduced with updated styling, technology, and performance over its predecessor.
  • 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: O22
Triple: [Columbia Airport, faaCode, O22]
Generated description
O22 is the Federal Aviation Administration location identifier assigned to Columbia Airport in the United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: O22
Target entity description: O22 is the Federal Aviation Administration location identifier assigned to Columbia Airport in the United States.
  • A. N222
    N222 is a regional road in the Netherlands that connects the town of Wateringen with surrounding areas in the Westland region.
  • B. E22
    E22 is a major European route that forms part of the international E-road network, linking multiple countries across Europe.
  • C. D22
    D22 is the second-generation Nissan Navara (also known as the Nissan Frontier in some markets), a compact pickup truck platform produced from the late 1990s into the 2000s.
  • D. N228
    N228 is a regional road in the Netherlands that provides access to and from the village of Benschop.
  • E. G22
    G22 is BMW’s internal model designation for the second-generation 4 Series coupe, introduced with updated styling, technology, and performance over its predecessor.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7dfcb508190aec8cd667e27a8ea completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dd746008190a7347368ee6d20cf completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fe9f671e788190b869aecb8e9d8f50 completed May 9, 2026, 2:43 a.m.
NED2 Entity disambiguation (via description) batch_69fe9fe08f408190b19f34e43d04311b completed May 9, 2026, 2:45 a.m.
Created at: April 10, 2026, 2:58 a.m.