Triple

T7991631
Position Surface form Disambiguated ID Type / Status
Subject Penn–North station E186019 entity
Predicate hasStationCode P1289 FINISHED
Object PN
PN is the station code for Penn–North station on the Baltimore Metro SubwayLink system.
 E703680 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: PN | Statement: [Penn–North station, hasStationCode, PN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PN
Context triple: [Penn–North station, hasStationCode, PN]
  • A. PN
    PN is the official abbreviation for the Philippine Navy, the naval warfare branch of the Armed Forces of the Philippines.
  • B. PN
    PN is the commonly used abbreviation for the National Parliament of East Timor, the country's unicameral legislative body.
  • C. PN
    PN is the vehicle registration code used for the Italian city and province of Pordenone in the Friuli Venezia Giulia region.
  • D. PNP
    The PNP is the national law enforcement agency of Peru responsible for maintaining public order, preventing and investigating crime, and ensuring internal security across the country.
  • E. P
    P is the vehicle registration code used on license plates for the Lithuanian city of Panevėžys.
  • 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: PN
Triple: [Penn–North station, hasStationCode, PN]
Generated description
PN is the station code for Penn–North station on the Baltimore Metro SubwayLink system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PN
Target entity description: PN is the station code for Penn–North station on the Baltimore Metro SubwayLink system.
  • A. PN
    PN is the official abbreviation for the Philippine Navy, the naval warfare branch of the Armed Forces of the Philippines.
  • B. PN
    PN is the vehicle registration code used for the Italian city and province of Pordenone in the Friuli Venezia Giulia region.
  • C. PN
    PN is the commonly used abbreviation for the National Parliament of East Timor, the country's unicameral legislative body.
  • D. PNP
    The PNP is the national law enforcement agency of Peru responsible for maintaining public order, preventing and investigating crime, and ensuring internal security across the country.
  • E. P
    P is the vehicle registration code used on license plates for the Lithuanian city of Panevėžys.
  • 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_69ca829c6c308190ab05b43d234c52b2 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c712d0481908d163d2509d054fa completed March 31, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe0fe312c81908c6874fa0aabe7d5 completed March 31, 2026, 2:58 p.m.
NEDg Description generation batch_69cbe440a66c8190a5d5b417fb5082b7 completed March 31, 2026, 3:12 p.m.
NED2 Entity disambiguation (via description) batch_69cc338a1c48819086ece073e04e8fa6 completed March 31, 2026, 8:50 p.m.
Created at: March 30, 2026, 5:16 p.m.