Triple

T11884653
Position Surface form Disambiguated ID Type / Status
Subject Pulkovo Airport E282747 entity
Predicate ICAOcode P419 FINISHED
Object ULLI
ULLI is the ICAO airport code for Pulkovo Airport, the main international airport serving Saint Petersburg, Russia.
 E952015 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: ULLI | Statement: [Pulkovo Airport, ICAOcode, ULLI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ULLI
Context triple: [Pulkovo Airport, ICAOcode, ULLI]
  • A. UL
    UL is the two-letter IATA airline designator assigned to SriLankan Airlines, the flag carrier of Sri Lanka.
  • B. UL
    UL is the New York Stock Exchange ticker symbol for Unilever, a major multinational consumer goods company known for its food, personal care, and household products.
  • C. UL
    UL is the vehicle registration code for the district that includes the municipality of Lauterach in Austria.
  • D. UL
    UL is the vehicle registration code used on license plates for the city of Ulm in Germany.
  • E. ULL
    ULL is the commonly used abbreviation for the University of La Laguna, a public higher education institution located in the Canary Islands, Spain.
  • 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: ULLI
Triple: [Pulkovo Airport, ICAOcode, ULLI]
Generated description
ULLI is the ICAO airport code for Pulkovo Airport, the main international airport serving Saint Petersburg, Russia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ULLI
Target entity description: ULLI is the ICAO airport code for Pulkovo Airport, the main international airport serving Saint Petersburg, Russia.
  • A. UL
    UL is the vehicle registration code used on license plates for the city of Ulm in Germany.
  • B. UL
    UL is the two-letter IATA airline designator assigned to SriLankan Airlines, the flag carrier of Sri Lanka.
  • C. UL
    UL is the New York Stock Exchange ticker symbol for Unilever, a major multinational consumer goods company known for its food, personal care, and household products.
  • D. UL
    UL is the vehicle registration code for the district that includes the municipality of Lauterach in Austria.
  • E. ULL
    ULL is the commonly used abbreviation for the University of La Laguna, a public higher education institution located in the Canary Islands, Spain.
  • 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_69d6ab2a90b08190a4e818821cc93e6d completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8d3a02ad4819090faef0e0be732ee completed April 10, 2026, 10:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69f281f488a8819082f40dfdd12f29a2 completed April 29, 2026, 10:11 p.m.
NEDg Description generation batch_69f2d6da770481908cd8787ba6b5763b completed April 30, 2026, 4:13 a.m.
NED2 Entity disambiguation (via description) batch_69f2dc57c3888190920b4275ed0b5bff completed April 30, 2026, 4:36 a.m.
Created at: April 8, 2026, 9:44 p.m.