Triple

T17655471
Position Surface form Disambiguated ID Type / Status
Subject Pohořelice E429610 entity
Predicate hasTransport P1298 FINISHED
Object road I/53
Road I/53 is a Czech first-class highway that serves as a key regional route connecting Pohořelice with southern Moravian towns and the Austrian border.
 E1281734 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: road I/53 | Statement: [Pohořelice, hasTransport, road I/53]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: road I/53
Context triple: [Pohořelice, hasTransport, road I/53]
  • A. road I/52
    Road I/52 is a major Czech roadway connecting Brno with the Austrian border near Mikulov, serving as an important regional and international transport route.
  • B. road I/59
    Road I/59 is a major Slovak roadway that serves as an important north–south transport route through the mountainous Donovaly region.
  • C. road I/38
    Road I/38 is a major Czech first-class highway that connects several important towns and regions in the central part of the country.
  • D. I-335
    I-335 is a segment of the Kansas Turnpike that forms part of the Interstate Highway System, connecting Emporia and Topeka in eastern Kansas.
  • E. Route I-50
    Route I-50 is a major roadway that provides key regional access to and from the city of San Fernando.
  • 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: road I/53
Triple: [Pohořelice, hasTransport, road I/53]
Generated description
Road I/53 is a Czech first-class highway that serves as a key regional route connecting Pohořelice with southern Moravian towns and the Austrian border.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: road I/53
Target entity description: Road I/53 is a Czech first-class highway that serves as a key regional route connecting Pohořelice with southern Moravian towns and the Austrian border.
  • A. road I/52
    Road I/52 is a major Czech roadway connecting Brno with the Austrian border near Mikulov, serving as an important regional and international transport route.
  • B. road I/59
    Road I/59 is a major Slovak roadway that serves as an important north–south transport route through the mountainous Donovaly region.
  • C. road I/38
    Road I/38 is a major Czech first-class highway that connects several important towns and regions in the central part of the country.
  • D. I-335
    I-335 is a segment of the Kansas Turnpike that forms part of the Interstate Highway System, connecting Emporia and Topeka in eastern Kansas.
  • E. Route I-50
    Route I-50 is a major roadway that provides key regional access to and from the city of San Fernando.
  • 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_69d889e2c2608190b762e76d9b2262f1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46e40e344819086a49c69f8f2956b completed April 19, 2026, 5:55 a.m.
NED1 Entity disambiguation (via context triple) batch_6a02231e338081908c54ac295290b417 completed May 11, 2026, 6:42 p.m.
NEDg Description generation batch_6a0225108620819080c7ee956177767c completed May 11, 2026, 6:50 p.m.
NED2 Entity disambiguation (via description) batch_6a0225ae3ec08190ba86f9aff74c653f completed May 11, 2026, 6:53 p.m.
Created at: April 10, 2026, 6:06 a.m.