Triple

T29902143
Position Surface form Disambiguated ID Type / Status
Subject Mumbai CSMT E759435 entity
Predicate previousStationCode P75590 FINISHED
Object CSTM
CSTM is the former station code for Mumbai's historic Chhatrapati Shivaji Maharaj Terminus, a major railway hub and UNESCO World Heritage Site in India.
 E1890324 NE FINISHED

How this triple was built (3 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: CSTM | Statement: [Mumbai CSMT, previousStationCode, CSTM]
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: CSTM
Triple: [Mumbai CSMT, previousStationCode, CSTM]
Generated description
CSTM is the former station code for Mumbai's historic Chhatrapati Shivaji Maharaj Terminus, a major railway hub and UNESCO World Heritage Site in India.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: previousStationCode
Context triple: [Mumbai CSMT, previousStationCode, CSTM]
  • A. precedingStation
    Indicates that one station is located immediately before another station in a route or sequence.
  • B. formerStationCode chosen
    Indicates that an entity previously had a specific station code that is no longer in current use.
  • C. previousStationOnLine1
    Indicates that one station is the immediately preceding station to another station along transit line 1.
  • D. previousStationOnLineA
    Indicates that one station is immediately before another station along line A in the route order.
  • E. precedingStationTowards
    Indicates that one station is immediately before another station along a specified direction or route toward a given destination.
  • F. None of above.

Provenance (6 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_69f224600590819085e148a01c056ef6 completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69fd974d75e08190af46b1d608769f3b completed May 8, 2026, 7:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a26f1e9725c819087be878f8259a9b2 completed June 8, 2026, 4:46 p.m.
NEDg Description generation batch_6a26f3456d8481909613c72f4f0b99ec completed June 8, 2026, 4:52 p.m.
NED2 Entity disambiguation (via description) batch_6a26f400153481909afc16df890350c1 completed June 8, 2026, 4:55 p.m.
PD Predicate disambiguation batch_69fd94ff792c8190bedf4a639d3da809 completed May 8, 2026, 7:47 a.m.
Created at: April 29, 2026, 6:07 p.m.