Triple

T1184684
Position Surface form Disambiguated ID Type / Status
Subject Gorlice E25217 entity
Predicate vehicleRegistrationCode P1173 FINISHED
Object KGR
KGR is the Polish vehicle registration code assigned to the Gorlice area in the Lesser Poland Voivodeship.
 E135716 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: KGR | Statement: [Gorlice, vehicleRegistrationCode, KGR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KGR
Context triple: [Gorlice, vehicleRegistrationCode, KGR]
  • A. KGH
    KGH is the National Rail station code for Kinghorn railway station in Fife, Scotland.
  • B. KG
    KG is the post-nominal abbreviation used by Knights of the Order of the Garter, the highest order of chivalry in the United Kingdom.
  • C. KG
    KG is the widely used nickname of Kevin Garnett, a Hall of Fame NBA forward known for his intensity, defensive prowess, and versatility.
  • D. Koreiz
    Koreiz is a resort settlement on the southern coast of Crimea, known for its seaside location and historic villas.
  • E. KI
    KI is the abbreviation for the Karolinska Institute, a renowned Swedish medical university known for its leading research and role in selecting Nobel laureates in Physiology or Medicine.
  • 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: KGR
Triple: [Gorlice, vehicleRegistrationCode, KGR]
Generated description
KGR is the Polish vehicle registration code assigned to the Gorlice area in the Lesser Poland Voivodeship.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KGR
Target entity description: KGR is the Polish vehicle registration code assigned to the Gorlice area in the Lesser Poland Voivodeship.
  • A. KGH
    KGH is the National Rail station code for Kinghorn railway station in Fife, Scotland.
  • B. KG
    KG is the post-nominal abbreviation used by Knights of the Order of the Garter, the highest order of chivalry in the United Kingdom.
  • C. KG
    KG is the widely used nickname of Kevin Garnett, a Hall of Fame NBA forward known for his intensity, defensive prowess, and versatility.
  • D. Koreiz
    Koreiz is a resort settlement on the southern coast of Crimea, known for its seaside location and historic villas.
  • E. KI
    KI is the abbreviation for the Karolinska Institute, a renowned Swedish medical university known for its leading research and role in selecting Nobel laureates in Physiology or Medicine.
  • 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_69a49427d98881908646d6c63b8cea1e completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd39245881908766c41943dc2752 completed March 1, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac6f239a288190ae488d11cff8ebf2 completed March 7, 2026, 6:32 p.m.
NEDg Description generation batch_69ac6fea11408190b84d9fc54d4c4917 completed March 7, 2026, 6:35 p.m.
NED2 Entity disambiguation (via description) batch_69ac70592c5c8190a1f86378ec5f70a9 completed March 7, 2026, 6:37 p.m.
Created at: March 1, 2026, 7:45 p.m.