Triple

T14452030
Position Surface form Disambiguated ID Type / Status
Subject Kangra Airport E358360 entity
Predicate IATAcode P418 FINISHED
Object DHM
DHM is the IATA airport code for Kangra Airport, a regional airport serving Dharamshala and the surrounding Kangra Valley in Himachal Pradesh, India.
E1098907 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: DHM | Statement: [Kangra Airport, IATAcode, DHM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DHM
Context triple: [Kangra Airport, IATAcode, DHM]
  • A. DHM
    DHM is the National Rail station code for Durham railway station in County Durham, England.
  • B. DHM
    DHM is the commonly used abbreviation for the German Historical Museum in Berlin, a major institution dedicated to documenting and presenting German history.
  • C. DHMİ
    DHMİ is Turkey’s state-owned General Directorate of State Airports Authority, responsible for operating and managing the country’s major airports and air navigation services.
  • D. DMH
    DMH is the Massachusetts state agency responsible for overseeing and providing public mental health services and supports.
  • E. HdM
    HdM is the commonly used abbreviation for Stuttgart Media University, a German university specializing in media, information, and communication studies.
  • 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: DHM
Triple: [Kangra Airport, IATAcode, DHM]
Generated description
DHM is the IATA airport code for Kangra Airport, a regional airport serving Dharamshala and the surrounding Kangra Valley in Himachal Pradesh, India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: DHM
Target entity description: DHM is the IATA airport code for Kangra Airport, a regional airport serving Dharamshala and the surrounding Kangra Valley in Himachal Pradesh, India.
  • A. DHM
    DHM is the commonly used abbreviation for the German Historical Museum in Berlin, a major institution dedicated to documenting and presenting German history.
  • B. DHM
    DHM is the National Rail station code for Durham railway station in County Durham, England.
  • C. DHMİ
    DHMİ is Turkey’s state-owned General Directorate of State Airports Authority, responsible for operating and managing the country’s major airports and air navigation services.
  • D. DMH
    DMH is the Massachusetts state agency responsible for overseeing and providing public mental health services and supports.
  • E. HdM
    HdM is the commonly used abbreviation for Stuttgart Media University, a German university specializing in media, information, and communication studies.
  • 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_69d82794dfa081909b9134ad2e32244b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de916244948190bb09d1bfc485ba50 completed April 14, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5be12da481909b11290965ec48da completed May 8, 2026, 3:43 a.m.
NEDg Description generation batch_69fd5de2ebac81908042f6696400a74d completed May 8, 2026, 3:52 a.m.
NED2 Entity disambiguation (via description) batch_69fd5e6927c88190add8d31989bec043 completed May 8, 2026, 3:54 a.m.
Created at: April 10, 2026, 1:19 a.m.