Triple

T13667012
Position Surface form Disambiguated ID Type / Status
Subject South Ealing station E327146 entity
Predicate hasStationCode P1289 FINISHED
Object SOE
SOE is the National Rail station code assigned to South Ealing station in London.
 E1052349 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: SOE | Statement: [South Ealing station, hasStationCode, SOE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SOE
Context triple: [South Ealing station, hasStationCode, SOE]
  • A. SOE
    SOE was a secret British World War II organization responsible for espionage, sabotage, and supporting resistance movements in enemy-occupied territories.
  • B. Soe
    Soe is a town in West Timor, Indonesia, known as an administrative and commercial center in the island’s interior highlands.
  • C. SOF
    SOF refers to Jordan’s elite Special Operations Forces, a highly trained military unit specializing in counterterrorism, unconventional warfare, and rapid-response missions.
  • D. SOF
    SOF is the three-letter IATA airport code for Sofia Airport, the main international airport serving Sofia, the capital of Bulgaria.
  • E. SOF
    SOF is the abbreviation for the Belgian Special Operations Forces, an elite military unit specializing in high-risk, strategic missions.
  • 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: SOE
Triple: [South Ealing station, hasStationCode, SOE]
Generated description
SOE is the National Rail station code assigned to South Ealing station in London.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SOE
Target entity description: SOE is the National Rail station code assigned to South Ealing station in London.
  • A. SOE
    SOE was a secret British World War II organization responsible for espionage, sabotage, and supporting resistance movements in enemy-occupied territories.
  • B. Soe
    Soe is a town in West Timor, Indonesia, known as an administrative and commercial center in the island’s interior highlands.
  • C. SOF
    SOF refers to Jordan’s elite Special Operations Forces, a highly trained military unit specializing in counterterrorism, unconventional warfare, and rapid-response missions.
  • D. SOF
    SOF is the three-letter IATA airport code for Sofia Airport, the main international airport serving Sofia, the capital of Bulgaria.
  • E. SOF
    SOF is the abbreviation for the Belgian Special Operations Forces, an elite military unit specializing in high-risk, strategic missions.
  • 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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc623fcc88190bbad97541c040b7a completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78b0cfe0c8190b0fe50931e9788cf completed May 3, 2026, 5:51 p.m.
NEDg Description generation batch_69f78bd727048190a57a75294a9ab53d completed May 3, 2026, 5:54 p.m.
NED2 Entity disambiguation (via description) batch_69f78c9f543481909a0de6a0c3bb041f completed May 3, 2026, 5:57 p.m.
Created at: April 9, 2026, 9:52 p.m.