Triple

T19116754
Position Surface form Disambiguated ID Type / Status
Subject GMP E467925 entity
Predicate UNLocode P1800 FINISHED
Object KR GMP
KR GMP is the UN/LOCODE identifying the port of Gunsan in South Korea for international trade and transport logistics.
 E1359223 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: KR GMP | Statement: [GMP, UNLocode, KR GMP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KR GMP
Context triple: [GMP, UNLocode, KR GMP]
  • A. KGM
    KGM is the Turkish General Directorate of Highways, the national authority responsible for planning, constructing, and maintaining Turkey’s road network.
  • B. KGM
    KGM is the three-letter National Rail station code assigned to Kingham railway station in Oxfordshire, England.
  • C. KGRK
    KGRK is the ICAO airport code for Robert Gray Army Airfield, a U.S. military airfield located near Killeen, Texas.
  • D. KGR
    KGR is the Polish vehicle registration code assigned to the Gorlice area in the Lesser Poland Voivodeship.
  • E. KM.G
    KM.G is a hip-hop producer and member of the Compton-based group Above the Law, known for his work shaping the early West Coast G-funk sound.
  • 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: KR GMP
Triple: [GMP, UNLocode, KR GMP]
Generated description
KR GMP is the UN/LOCODE identifying the port of Gunsan in South Korea for international trade and transport logistics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KR GMP
Target entity description: KR GMP is the UN/LOCODE identifying the port of Gunsan in South Korea for international trade and transport logistics.
  • A. KGM
    KGM is the Turkish General Directorate of Highways, the national authority responsible for planning, constructing, and maintaining Turkey’s road network.
  • B. KGM
    KGM is the three-letter National Rail station code assigned to Kingham railway station in Oxfordshire, England.
  • C. KGRK
    KGRK is the ICAO airport code for Robert Gray Army Airfield, a U.S. military airfield located near Killeen, Texas.
  • D. KGR
    KGR is the Polish vehicle registration code assigned to the Gorlice area in the Lesser Poland Voivodeship.
  • E. KM.G
    KM.G is a hip-hop producer and member of the Compton-based group Above the Law, known for his work shaping the early West Coast G-funk sound.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3984bf48190818fa2b01b75decb completed April 20, 2026, 8:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05e671f2988190a74d53989124026b completed May 14, 2026, 3:12 p.m.
NEDg Description generation batch_6a05e9406ba48190a50f4ea6b413e1f4 completed May 14, 2026, 3:24 p.m.
NED2 Entity disambiguation (via description) batch_6a05e9c0d35081909b6ce3c287af5d5f completed May 14, 2026, 3:26 p.m.
Created at: April 10, 2026, 12:05 p.m.