Triple

T21206716
Position Surface form Disambiguated ID Type / Status
Subject Pakleni Islands E522603 entity
Predicate hasMajorIsland P756 FINISHED
Object Mlini
Mlini is one of the main islands in Croatia’s Pakleni Islands archipelago, known for its clear waters and secluded coves popular with boaters and swimmers.
E1472093 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: Mlini | Statement: [Pakleni Islands, hasMajorIsland, Mlini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mlini
Context triple: [Pakleni Islands, hasMajorIsland, Mlini]
  • A. Mlino
    Mlino is a small settlement in northwestern Slovenia, situated near Lake Bled within the Municipality of Bled.
  • B. Mzilikazi
    Mzilikazi was a 19th-century Southern African king who founded the Ndebele (Matabele) nation and led its migration to what is now Zimbabwe.
  • C. Nkosi
    Nkosi is a traditional royal title used for rulers and chiefs among the Mpondo people of South Africa.
  • D. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • E. Mandla
    Mandla is a town and administrative district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to the Narmada River and nearby wildlife and forested areas.
  • 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: Mlini
Triple: [Pakleni Islands, hasMajorIsland, Mlini]
Generated description
Mlini is one of the main islands in Croatia’s Pakleni Islands archipelago, known for its clear waters and secluded coves popular with boaters and swimmers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mlini
Target entity description: Mlini is one of the main islands in Croatia’s Pakleni Islands archipelago, known for its clear waters and secluded coves popular with boaters and swimmers.
  • A. Mlino
    Mlino is a small settlement in northwestern Slovenia, situated near Lake Bled within the Municipality of Bled.
  • B. Mzilikazi
    Mzilikazi was a 19th-century Southern African king who founded the Ndebele (Matabele) nation and led its migration to what is now Zimbabwe.
  • C. Nkosi
    Nkosi is a traditional royal title used for rulers and chiefs among the Mpondo people of South Africa.
  • D. Mtiuleti
    Mtiuleti is a mountainous historical region in northeastern Georgia known for its rugged landscapes and traditional highland villages.
  • E. Mandla
    Mandla is a town and administrative district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to the Narmada River and nearby wildlife and forested areas.
  • 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_69e0b5112d8881909510b2dcdc93106d completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73435322c8190bf4156fbd14edc5c completed April 21, 2026, 8:24 a.m.
NED1 Entity disambiguation (via context triple) batch_6a097ed2c0b48190bcaf2937004abbfd completed May 17, 2026, 8:39 a.m.
NEDg Description generation batch_6a0980329bb4819088da49aec70f27a0 completed May 17, 2026, 8:45 a.m.
NED2 Entity disambiguation (via description) batch_6a0981b76b108190a0c9ae60c81bd4fc completed May 17, 2026, 8:52 a.m.
Created at: April 16, 2026, 3:20 p.m.