Triple

T14686950
Position Surface form Disambiguated ID Type / Status
Subject Warwick Farm railway station E344931 entity
Predicate hasStationCode P1289 FINISHED
Object WFM
WFM is the station code for Warwick Farm railway station, a suburban train station in Sydney, Australia.
 E1113953 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: WFM | Statement: [Warwick Farm railway station, hasStationCode, WFM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WFM
Context triple: [Warwick Farm railway station, hasStationCode, WFM]
  • A. WFM (former)
    WFM (former) was the stock ticker symbol under which Whole Foods Market was publicly traded before its acquisition by Amazon.
  • B. WFN
    WFN is the three-letter National Rail station code assigned to Watford North railway station in Hertfordshire, England.
  • C. FWN
    FWN is the Dutch abbreviation for the Faculty of Science at Leiden University, a major academic division focused on scientific research and education.
  • D. FWN
    FWN is the standard abbreviation used for the Fort Wayne TinCaps, a Minor League Baseball team based in Fort Wayne, Indiana.
  • E. WF
    WF is the common abbreviation for Wikifunctions, a Wikimedia project aimed at creating a collaborative catalog of reusable functions.
  • 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: WFM
Triple: [Warwick Farm railway station, hasStationCode, WFM]
Generated description
WFM is the station code for Warwick Farm railway station, a suburban train station in Sydney, Australia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WFM
Target entity description: WFM is the station code for Warwick Farm railway station, a suburban train station in Sydney, Australia.
  • A. WFM (former)
    WFM (former) was the stock ticker symbol under which Whole Foods Market was publicly traded before its acquisition by Amazon.
  • B. WFN
    WFN is the three-letter National Rail station code assigned to Watford North railway station in Hertfordshire, England.
  • C. FWN
    FWN is the Dutch abbreviation for the Faculty of Science at Leiden University, a major academic division focused on scientific research and education.
  • D. FWN
    FWN is the standard abbreviation used for the Fort Wayne TinCaps, a Minor League Baseball team based in Fort Wayne, Indiana.
  • E. WF
    WF is the common abbreviation for Wikifunctions, a Wikimedia project aimed at creating a collaborative catalog of reusable functions.
  • 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_69d822e34b348190ada4d1cdb6c7c226 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb58306548190b981956a83a84b95 completed April 14, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde1876fdc81908a4fe3deebb7ff83 completed May 8, 2026, 1:13 p.m.
NEDg Description generation batch_69fde6c7a8ac8190a80b6c6ed0b5b157 completed May 8, 2026, 1:36 p.m.
NED2 Entity disambiguation (via description) batch_69fde73ca1dc8190b7fc13d7ffb6daf4 completed May 8, 2026, 1:38 p.m.
Created at: April 10, 2026, 1:28 a.m.