Triple

T17481486
Position Surface form Disambiguated ID Type / Status
Subject Krkonoše National Park E425669 entity
Predicate abbreviation P43 FINISHED
Object KRNAP
KRNAP is the Czech abbreviation for Krkonoše National Park, a protected mountain area in the Krkonoše range known for its unique alpine ecosystems and popular outdoor recreation.
 E1270414 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: KRNAP | Statement: [Krkonoše National Park, abbreviation, KRNAP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KRNAP
Context triple: [Krkonoše National Park, abbreviation, KRNAP]
  • A. KRN
    KRN is the abbreviation for the Krajowa Rada Narodowa, the wartime Polish parliament established by communists in 1943 as a rival authority to the government-in-exile.
  • B. KNA
    KNA is the ICAO airline designator assigned to Kunming Airlines, a Chinese carrier based in Kunming, Yunnan.
  • C. KNA
    KNA is the three-letter ISO 3166-1 alpha-3 country code assigned to Saint Kitts and Nevis.
  • D. KRP
    KRP is the IATA airport code for Karup Airport, a regional airport in Denmark.
  • E. KRASP
    KRASP is the Polish acronym for the Conference of Rectors of Academic Schools in Poland, a national body representing the interests and coordination of university leaders.
  • 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: KRNAP
Triple: [Krkonoše National Park, abbreviation, KRNAP]
Generated description
KRNAP is the Czech abbreviation for Krkonoše National Park, a protected mountain area in the Krkonoše range known for its unique alpine ecosystems and popular outdoor recreation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KRNAP
Target entity description: KRNAP is the Czech abbreviation for Krkonoše National Park, a protected mountain area in the Krkonoše range known for its unique alpine ecosystems and popular outdoor recreation.
  • A. KRN
    KRN is the abbreviation for the Krajowa Rada Narodowa, the wartime Polish parliament established by communists in 1943 as a rival authority to the government-in-exile.
  • B. KNA
    KNA is the ICAO airline designator assigned to Kunming Airlines, a Chinese carrier based in Kunming, Yunnan.
  • C. KNA
    KNA is the three-letter ISO 3166-1 alpha-3 country code assigned to Saint Kitts and Nevis.
  • D. KRP
    KRP is the IATA airport code for Karup Airport, a regional airport in Denmark.
  • E. KRASP
    KRASP is the Polish acronym for the Conference of Rectors of Academic Schools in Poland, a national body representing the interests and coordination of university leaders.
  • 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451bfd75481908c20bc2c1cbff593 completed April 19, 2026, 3:53 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01b8320f488190a4eacfb628bb1dfd completed May 11, 2026, 11:06 a.m.
NEDg Description generation batch_6a01b8dd58f8819090d5138897c5155f completed May 11, 2026, 11:09 a.m.
NED2 Entity disambiguation (via description) batch_6a01b9676d54819098315611857dd6ea completed May 11, 2026, 11:11 a.m.
Created at: April 10, 2026, 5:48 a.m.