Triple

T18538399
Position Surface form Disambiguated ID Type / Status
Subject Midnapore railway station E453023 entity
Predicate railwayCode P18202 FINISHED
Object MDN
MDN is the station code for Midnapore railway station on the Indian Railways network.
E1329507 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: MDN | Statement: [Midnapore railway station, railwayCode, MDN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MDN
Context triple: [Midnapore railway station, railwayCode, MDN]
  • A. MDN
    MDN is the vehicle registration code assigned to Mardan, a city in the Khyber Pakhtunkhwa province of Pakistan.
  • B. MDN
    MDN is the commonly used abbreviation for Portugal’s Ministry of National Defence, the government body responsible for the country’s defense policy and armed forces.
  • C. MDN
    MDN is the commonly used abbreviation for Chile's Ministry of National Defense, the government body responsible for overseeing the country's armed forces and defense policy.
  • D. MDN Web Docs
    MDN Web Docs is a comprehensive, community-driven documentation resource for web technologies such as HTML, CSS, and JavaScript, widely used by developers to learn and reference open web standards.
  • E. Mozilla developer tools
    Mozilla developer tools are the built-in web development and debugging tools in the Firefox browser, providing features like an inspector, console, debugger, and network monitor for web developers.
  • 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: MDN
Triple: [Midnapore railway station, railwayCode, MDN]
Generated description
MDN is the station code for Midnapore railway station on the Indian Railways network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MDN
Target entity description: MDN is the station code for Midnapore railway station on the Indian Railways network.
  • A. MDN
    MDN is the vehicle registration code assigned to Mardan, a city in the Khyber Pakhtunkhwa province of Pakistan.
  • B. MDN
    MDN is the commonly used abbreviation for Portugal’s Ministry of National Defence, the government body responsible for the country’s defense policy and armed forces.
  • C. MDN
    MDN is the commonly used abbreviation for Chile's Ministry of National Defense, the government body responsible for overseeing the country's armed forces and defense policy.
  • D. MDN Web Docs
    MDN Web Docs is a comprehensive, community-driven documentation resource for web technologies such as HTML, CSS, and JavaScript, widely used by developers to learn and reference open web standards.
  • E. Mozilla developer tools
    Mozilla developer tools are the built-in web development and debugging tools in the Firefox browser, providing features like an inspector, console, debugger, and network monitor for web developers.
  • 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_69d8d387b5548190aa030dad2cb4947e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e534030bd88190b25b95305a12a0c1 completed April 19, 2026, 7:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a04917f770c8190b25da102a3368828 completed May 13, 2026, 2:58 p.m.
NEDg Description generation batch_6a0493595bec8190b92e737effb91f54 completed May 13, 2026, 3:06 p.m.
NED2 Entity disambiguation (via description) batch_6a04941c17988190b38bfce00fedbeca completed May 13, 2026, 3:09 p.m.
Created at: April 10, 2026, 11:37 a.m.