Triple

T15429102
Position Surface form Disambiguated ID Type / Status
Subject Milan Metro Line 3 E369587 entity
Predicate station P726 FINISHED
Object Porta Romana
Porta Romana is an underground station on Milan’s Metro Line 3 serving the historic Porta Romana district south of the city center.
E1156282 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: Porta Romana | Statement: [Milan Metro Line 3, station, Porta Romana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Porta Romana
Context triple: [Milan Metro Line 3, station, Porta Romana]
  • A. Porta Romana
    Porta Romana is a historic city gate in Viterbo, Italy, serving as one of the traditional entrances through the town’s medieval walls.
  • B. Porta Romana
    Porta Romana is a historic city gate in Velletri, Italy, notable as one of the traditional entrances to the town.
  • C. Porta Romana
    Porta Romana is a historic city gate in Norcia, Italy, notable as one of the main entrances through the town’s medieval walls.
  • D. Porta Romana
    Porta Romana is a historic city gate of Terra del Sole in Italy, notable as one of the main fortified entrances to the Renaissance-planned town.
  • E. Porta Romana
    Porta Romana is a historic town gate in Valentano, Italy, notable as one of the main entrances to its old medieval center.
  • 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: Porta Romana
Triple: [Milan Metro Line 3, station, Porta Romana]
Generated description
Porta Romana is an underground station on Milan’s Metro Line 3 serving the historic Porta Romana district south of the city center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Porta Romana
Target entity description: Porta Romana is an underground station on Milan’s Metro Line 3 serving the historic Porta Romana district south of the city center.
  • A. Porta Romana
    Porta Romana is a historic city gate and surrounding district in Milan, Italy, known for its architectural heritage and vibrant urban life.
  • B. Porta Romana
    Porta Romana is a historic city gate in Velletri, Italy, notable as one of the traditional entrances to the town.
  • C. Porta Romana
    Porta Romana is a historic town gate in Valentano, Italy, notable as one of the main entrances to its old medieval center.
  • D. Porta Romana
    Porta Romana is a historic city gate in Viterbo, Italy, serving as one of the traditional entrances through the town’s medieval walls.
  • E. Porta Romana
    Porta Romana is a historic city gate in Norcia, Italy, notable as one of the main entrances through the town’s medieval walls.
  • 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_69d85a1849f48190bf898068b2806fae completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ec31f4881908b26ff7c381d7bc9 completed April 16, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff1a827d9081909fabc48bc685ba5b completed May 9, 2026, 11:29 a.m.
NEDg Description generation batch_69ff1b4c13e08190b2ccee59da02d0ae completed May 9, 2026, 11:32 a.m.
NED2 Entity disambiguation (via description) batch_69ff1bdb39b481908f0b1df595837bc4 completed May 9, 2026, 11:34 a.m.
Created at: April 10, 2026, 3:21 a.m.