Triple

T18814867
Position Surface form Disambiguated ID Type / Status
Subject Punat E460108 entity
Predicate hasMarina P3007 FINISHED
Object Marina Punat
Marina Punat is a well-known yacht marina and nautical tourism center located near the town of Punat on the island of Krk in Croatia.
E1343793 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: Marina Punat | Statement: [Punat, hasMarina, Marina Punat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marina Punat
Context triple: [Punat, hasMarina, Marina Punat]
  • A. Marina Sbisa
    Marina Sbisa is an Italian philosopher and linguist known for her influential work in pragmatics and speech act theory.
  • B. Marina Zadar
    Marina Zadar is a coastal marina in the Croatian city of Zadar, serving as a popular docking and service hub for yachts and boats in the Adriatic Sea.
  • C. Marina Chapelin
    Marina Chapelin is a coastal marina in Varadero, Cuba, serving as a docking and service hub for recreational boats and yachts.
  • D. Marina Severa
    Marina Severa was a Roman empress of the 4th century, known as the first wife of Emperor Valentinian I and the mother of Emperor Gratian.
  • E. Marina Lu
    Marina Lu is the mother of renowned cellist Yo-Yo Ma.
  • 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: Marina Punat
Triple: [Punat, hasMarina, Marina Punat]
Generated description
Marina Punat is a well-known yacht marina and nautical tourism center located near the town of Punat on the island of Krk in Croatia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marina Punat
Target entity description: Marina Punat is a well-known yacht marina and nautical tourism center located near the town of Punat on the island of Krk in Croatia.
  • A. Marina Sbisa
    Marina Sbisa is an Italian philosopher and linguist known for her influential work in pragmatics and speech act theory.
  • B. Marina Zadar
    Marina Zadar is a coastal marina in the Croatian city of Zadar, serving as a popular docking and service hub for yachts and boats in the Adriatic Sea.
  • C. Marina Chapelin
    Marina Chapelin is a coastal marina in Varadero, Cuba, serving as a docking and service hub for recreational boats and yachts.
  • D. Marina Severa
    Marina Severa was a Roman empress of the 4th century, known as the first wife of Emperor Valentinian I and the mother of Emperor Gratian.
  • E. Marina Lu
    Marina Lu is the mother of renowned cellist Yo-Yo Ma.
  • 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_69d8d398c7d4819091cb2f7e48948aeb completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5a3df2d3881909b336d813bbfd0aa completed April 20, 2026, 3:56 a.m.
NED1 Entity disambiguation (via context triple) batch_6a055bc7cf40819084b9b975daa86b5f completed May 14, 2026, 5:21 a.m.
NEDg Description generation batch_6a055d9a9da88190b974e8803ca8537f completed May 14, 2026, 5:28 a.m.
NED2 Entity disambiguation (via description) batch_6a055e1a22308190bb7f2337fabc5bdf completed May 14, 2026, 5:31 a.m.
Created at: April 10, 2026, 11:53 a.m.