Triple

T19298031
Position Surface form Disambiguated ID Type / Status
Subject Solna centrum metro station E482617 entity
Predicate hasStationCode P1289 FINISHED
Object SAC
SAC is the station code used to identify Solna centrum on the Stockholm metro system.
E1369024 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: SAC | Statement: [Solna centrum metro station, hasStationCode, SAC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SAC
Context triple: [Solna centrum metro station, hasStationCode, SAC]
  • A. SAC
    SAC is the commonly used abbreviation for the Sheriff Appeal Court, a Scottish appellate court that hears civil and criminal appeals from sheriff courts.
  • B. SAC
    SAC (Soft Actor-Critic) is a popular off-policy deep reinforcement learning algorithm that optimizes both expected return and policy entropy to achieve stable and efficient learning in continuous control tasks.
  • C. SAC
    SAC is the commonly used abbreviation for the United States Air Force’s former Strategic Air Command, which oversaw America’s land-based nuclear bombers and missiles during much of the Cold War.
  • D. SAC
    The SAC is the abbreviated name commonly used for the State Affairs Commission, the top governing body in North Korea responsible for major state policy and leadership.
  • E. SAC
    The SAC is Myanmar’s military junta that seized power in the 2021 coup and has since served as the country’s de facto governing authority.
  • 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: SAC
Triple: [Solna centrum metro station, hasStationCode, SAC]
Generated description
SAC is the station code used to identify Solna centrum on the Stockholm metro system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SAC
Target entity description: SAC is the station code used to identify Solna centrum on the Stockholm metro system.
  • A. SAC
    SAC is the National Rail station code for St Albans City railway station in Hertfordshire, England.
  • B. SAC
    SAC is the three-letter IATA airport code assigned to Sacramento Executive Airport in Sacramento, California.
  • C. SAC
    SAC is the company that manages Catania–Fontanarossa Airport, one of the main air transport hubs in Sicily, Italy.
  • D. SAC
    SAC is the commonly used abbreviation for the Sheriff Appeal Court, a Scottish appellate court that hears civil and criminal appeals from sheriff courts.
  • E. SAC
    SAC is the commonly used abbreviation for the United States Air Force’s former Strategic Air Command, which oversaw America’s land-based nuclear bombers and missiles during much of the Cold War.
  • 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_69d8e8cf61b0819096fe3e4107827c4e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc86f8648190920d122bb141c6e5 completed April 20, 2026, 10:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a07145350108190b99022e887a4193f completed May 15, 2026, 12:40 p.m.
NEDg Description generation batch_6a071539637081909eb54bc2553c47b9 completed May 15, 2026, 12:44 p.m.
NED2 Entity disambiguation (via description) batch_6a07161b27e4819088745c7f1c169416 completed May 15, 2026, 12:48 p.m.
Created at: April 10, 2026, 1:31 p.m.