Triple

T16991240
Position Surface form Disambiguated ID Type / Status
Subject Marjan Hill E412197 entity
Predicate adjacentTo P224 FINISHED
Object Split city center
Split city center is the historic core of the Croatian coastal city of Split, known for Diocletian’s Palace, Roman and medieval architecture, and its lively waterfront promenade.
 E1245011 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: Split city center | Statement: [Marjan Hill, adjacentTo, Split city center]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Split city center
Context triple: [Marjan Hill, adjacentTo, Split city center]
  • A. Como city center
    Como city center is the historic and commercial heart of the lakeside city of Como in northern Italy, known for its medieval streets, waterfront promenades, and proximity to Lake Como’s main attractions.
  • B. Centrum
    Centrum is the central district and main urban core of the Dutch municipality of Ridderkerk.
  • C. Centrum
    Centrum is the central urban district and main commercial area of the Dutch city of Meppel.
  • D. Centrum
    Centrum is the historic city center district of Amsterdam, known for its canals, landmarks, and bustling markets.
  • E. Innenstadt
    Innenstadt is the central urban district of Frankfurt am Main, known as the city’s historic core and primary commercial area.
  • 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: Split city center
Triple: [Marjan Hill, adjacentTo, Split city center]
Generated description
Split city center is the historic core of the Croatian coastal city of Split, known for Diocletian’s Palace, Roman and medieval architecture, and its lively waterfront promenade.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Split city center
Target entity description: Split city center is the historic core of the Croatian coastal city of Split, known for Diocletian’s Palace, Roman and medieval architecture, and its lively waterfront promenade.
  • A. Como city center
    Como city center is the historic and commercial heart of the lakeside city of Como in northern Italy, known for its medieval streets, waterfront promenades, and proximity to Lake Como’s main attractions.
  • B. Centrum
    Centrum is the central urban district and main commercial area of the Dutch city of Meppel.
  • C. Centrum
    Centrum is the central district and main urban core of the Dutch municipality of Ridderkerk.
  • D. Centrum
    Centrum is the historic city center district of Amsterdam, known for its canals, landmarks, and bustling markets.
  • E. Innenstadt
    Innenstadt is the central urban district of Frankfurt am Main, known as the city’s historic core and primary commercial area.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d280e3348190a27bd5dc7cf87c0e completed April 18, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dc14d5688190945f7ae72f724922 completed May 10, 2026, 7:27 p.m.
NEDg Description generation batch_6a0114d5aeb0819086f1a5d279ac0d0f completed May 10, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0115c967b0819088e2335fd45d755b completed May 10, 2026, 11:33 p.m.
Created at: April 10, 2026, 5:32 a.m.