Triple

T13084885
Position Surface form Disambiguated ID Type / Status
Subject Thorildsplan E310304 entity
Predicate hasStationCode P1289 FINISHED
Object THP
THP is the station code for Thorildsplan, a Stockholm metro station on the green line in Sweden.
 E1021093 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: THP | Statement: [Thorildsplan, hasStationCode, THP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: THP
Context triple: [Thorildsplan, hasStationCode, THP]
  • A. TH
    TH is the two-letter ISO 3166-1 alpha-2 country code assigned to Thailand for international standardization and identification.
  • B. THF
    THF is the former Berlin Tempelhof Airport, a historically significant airfield known for its role in the Berlin Airlift and its later conversion into a vast urban park.
  • C. THS
    THS is the stock ticker symbol for TreeHouse Foods, a U.S.-based manufacturer of private-label packaged foods and beverages.
  • D. TP
    TP is the two-letter IATA airline designator used to identify TAP Air Portugal on tickets, timetables, and flight information systems.
  • E. THPO
    THPO is the acronym for a Tribal Historic Preservation Office, the tribal agency responsible for protecting and managing a Native American tribe’s cultural and historic resources.
  • 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: THP
Triple: [Thorildsplan, hasStationCode, THP]
Generated description
THP is the station code for Thorildsplan, a Stockholm metro station on the green line in Sweden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: THP
Target entity description: THP is the station code for Thorildsplan, a Stockholm metro station on the green line in Sweden.
  • A. TH
    TH is the two-letter ISO 3166-1 alpha-2 country code assigned to Thailand for international standardization and identification.
  • B. THF
    THF is the former Berlin Tempelhof Airport, a historically significant airfield known for its role in the Berlin Airlift and its later conversion into a vast urban park.
  • C. THS
    THS is the stock ticker symbol for TreeHouse Foods, a U.S.-based manufacturer of private-label packaged foods and beverages.
  • D. TP
    TP is the two-letter IATA airline designator used to identify TAP Air Portugal on tickets, timetables, and flight information systems.
  • E. THPO
    THPO is the acronym for a Tribal Historic Preservation Office, the tribal agency responsible for protecting and managing a Native American tribe’s cultural and historic resources.
  • 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_69d806a733548190989cfd4ce981ca33 completed April 9, 2026, 8:05 p.m.
NER Named-entity recognition batch_69d981361e8c819099376435aa3a7aa3 completed April 10, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6d61060188190911eb3e135dc25ac completed May 3, 2026, 4:58 a.m.
NEDg Description generation batch_69f6dae595908190b27980e48514cda5 completed May 3, 2026, 5:19 a.m.
NED2 Entity disambiguation (via description) batch_69f6db8f68a4819091d8e67d9c8eec81 completed May 3, 2026, 5:22 a.m.
Created at: April 9, 2026, 9:02 p.m.