Triple

T20130057
Position Surface form Disambiguated ID Type / Status
Subject Sehore railway station E490864 entity
Predicate stationCode P1289 FINISHED
Object SEH
SEH is the station code for Sehore railway station, a rail transport facility serving the town of Sehore in the Indian state of Madhya Pradesh.
 E1412895 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: SEH | Statement: [Sehore railway station, stationCode, SEH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SEH
Context triple: [Sehore railway station, stationCode, SEH]
  • A. SEH
    SEH is the standard abbreviation for the South Eastern Highlands, a biogeographic region in southeastern Australia characterized by elevated terrain and diverse ecosystems.
  • B. SEH
    SEH is the ICAO airline designator assigned to Sky Express, a Greek regional airline.
  • C. SECC
    SECC is a major exhibition and conference complex in Glasgow, Scotland, known for hosting large-scale events, concerts, and trade shows.
  • D. SEV
    SEV is the National Rail station code for Sevenoaks railway station in Kent, England.
  • E. EHE
    EHE is the commonly used abbreviation for the College of Education and Human Ecology, an academic unit focused on teaching, research, and outreach in education and human development fields.
  • 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: SEH
Triple: [Sehore railway station, stationCode, SEH]
Generated description
SEH is the station code for Sehore railway station, a rail transport facility serving the town of Sehore in the Indian state of Madhya Pradesh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SEH
Target entity description: SEH is the station code for Sehore railway station, a rail transport facility serving the town of Sehore in the Indian state of Madhya Pradesh.
  • A. SEH
    SEH is the standard abbreviation for the South Eastern Highlands, a biogeographic region in southeastern Australia characterized by elevated terrain and diverse ecosystems.
  • B. SEH
    SEH is the ICAO airline designator assigned to Sky Express, a Greek regional airline.
  • C. SECC
    SECC is a major exhibition and conference complex in Glasgow, Scotland, known for hosting large-scale events, concerts, and trade shows.
  • D. SEV
    SEV is the National Rail station code for Sevenoaks railway station in Kent, England.
  • E. EHE
    EHE is the commonly used abbreviation for the College of Education and Human Ecology, an academic unit focused on teaching, research, and outreach in education and human development fields.
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6676183dc8190b65d0def681aaa1e completed April 20, 2026, 5:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a082dddf6388190b765f9092d2f035a completed May 16, 2026, 8:42 a.m.
NEDg Description generation batch_6a082e93a1e88190bac5daae12ece9f2 completed May 16, 2026, 8:45 a.m.
NED2 Entity disambiguation (via description) batch_6a082f334dd481908edb6ea3ae07e0a7 completed May 16, 2026, 8:47 a.m.
Created at: April 11, 2026, 11:31 p.m.