Triple

T13249038
Position Surface form Disambiguated ID Type / Status
Subject St Johns railway station E315478 entity
Predicate hasStationCode P1289 FINISHED
Object SAJ
SAJ is the National Rail station code for St Johns railway station in southeast London, England.
 E1029805 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: SAJ | Statement: [St Johns railway station, hasStationCode, SAJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAJ
Context triple: [St Johns railway station, hasStationCode, SAJ]
  • A. SAJ
    SAJ is a Jewish congregation and community in New York City historically associated with the Reconstructionist movement and progressive Jewish practice.
  • B. SAJ
    SAJ is the Ski Association of Japan, the national governing body for ski sports in Japan, including ski jumping.
  • C. SA3
    SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
  • D. SAIT
    SAIT is a Canadian polytechnic institute in Calgary, Alberta, offering career-focused technical, trades, and applied degree programs.
  • E. SAU
    SAU is an international university established by the South Asian Association for Regional Cooperation (SAARC) in New Delhi, India, focusing on postgraduate and doctoral education and research for students from South Asian countries.
  • 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: SAJ
Triple: [St Johns railway station, hasStationCode, SAJ]
Generated description
SAJ is the National Rail station code for St Johns railway station in southeast London, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SAJ
Target entity description: SAJ is the National Rail station code for St Johns railway station in southeast London, England.
  • A. SAJ
    SAJ is a Jewish congregation and community in New York City historically associated with the Reconstructionist movement and progressive Jewish practice.
  • B. SAJ
    SAJ is the Ski Association of Japan, the national governing body for ski sports in Japan, including ski jumping.
  • C. SA3
    SA3 is the 3GPP security working group responsible for specifying and evolving security architecture and mechanisms across mobile communication standards.
  • D. SAIT
    SAIT is a Canadian polytechnic institute in Calgary, Alberta, offering career-focused technical, trades, and applied degree programs.
  • E. SAU
    SAU is an international university established by the South Asian Association for Regional Cooperation (SAARC) in New Delhi, India, focusing on postgraduate and doctoral education and research for students from South Asian countries.
  • 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_69d806b1072881909e46bd212259c5f0 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98d9e7ea881908abc4b3a54896692 completed April 10, 2026, 11:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6ff37f7448190b9c555cae010d3b6 completed May 3, 2026, 7:54 a.m.
NEDg Description generation batch_69f70476310c8190b13dc948c1f1ce95 completed May 3, 2026, 8:16 a.m.
NED2 Entity disambiguation (via description) batch_69f70578047c819089fc3044eceb4eac completed May 3, 2026, 8:21 a.m.
Created at: April 9, 2026, 9:24 p.m.