Triple

T17133824
Position Surface form Disambiguated ID Type / Status
Subject Roman province of Dalmatia E415785 entity
Predicate majorCity P316 FINISHED
Object Narona
Narona was an important ancient Roman city and trading center in the province of Dalmatia, located near the mouth of the Neretva River in what is now southern Croatia.
 E1253031 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: Narona | Statement: [Roman province of Dalmatia, majorCity, Narona]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Narona
Context triple: [Roman province of Dalmatia, majorCity, Narona]
  • A. Novilara
    Novilara is an archaeological site and locality in the Marche region of Italy, known for its ancient Picene culture remains and notable funerary stelae.
  • B. Nassa
    Nassa is a small locality or hamlet that forms part of the municipality of Valfurva in northern Italy.
  • C. Cirra
    Cirra is an ancient Greek coastal town historically associated with the region around Crisa and the sanctuary of Delphi.
  • D. Loelva
    Loelva is a river flowing through Norway’s scenic Loen valley, known for its glacial origins and striking turquoise waters.
  • E. Arnara
    Arnara is a small municipality in the Lazio region of central Italy, located in the province of Frosinone.
  • 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: Narona
Triple: [Roman province of Dalmatia, majorCity, Narona]
Generated description
Narona was an important ancient Roman city and trading center in the province of Dalmatia, located near the mouth of the Neretva River in what is now southern Croatia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Narona
Target entity description: Narona was an important ancient Roman city and trading center in the province of Dalmatia, located near the mouth of the Neretva River in what is now southern Croatia.
  • A. Novilara
    Novilara is an archaeological site and locality in the Marche region of Italy, known for its ancient Picene culture remains and notable funerary stelae.
  • B. Nassa
    Nassa is a small locality or hamlet that forms part of the municipality of Valfurva in northern Italy.
  • C. Cirra
    Cirra is an ancient Greek coastal town historically associated with the region around Crisa and the sanctuary of Delphi.
  • D. Loelva
    Loelva is a river flowing through Norway’s scenic Loen valley, known for its glacial origins and striking turquoise waters.
  • E. Arnara
    Arnara is a small municipality in the Lazio region of central Italy, located in the province of Frosinone.
  • 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_69d886d15af4819092f92f8a129763e6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f02cbb7881908aa69c3443d149d5 completed April 18, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01414eca3c8190aeec22fab3b5e767 completed May 11, 2026, 2:39 a.m.
NEDg Description generation batch_6a01423a771881908c2eaff14e335ee2 completed May 11, 2026, 2:43 a.m.
NED2 Entity disambiguation (via description) batch_6a01430b7e008190bc3366cc89564409 completed May 11, 2026, 2:46 a.m.
Created at: April 10, 2026, 5:36 a.m.