Triple

T9182636
Position Surface form Disambiguated ID Type / Status
Subject Lolland E220370 entity
Predicate hasCapital P204 FINISHED
Object Maribo
Maribo is a historic market town on the Danish island of Lolland, known for its cathedral and lakeside setting.
E784207 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: Maribo | Statement: [Lolland, hasCapital, Maribo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maribo
Context triple: [Lolland, hasCapital, Maribo]
  • A. Seskarö
    Seskarö is a Swedish island in the northern Baltic Sea known for its forests, beaches, and traditional fishing and forestry communities.
  • B. Kamarina
    Kamarina is a modern settlement in the Epirus region of northwestern Greece, located near the archaeological site of ancient Cassope.
  • C. Minskov
    Minskov is a supporting character in the French crime drama film "The Beat That My Heart Skipped," involved in the criminal underworld that complicates the protagonist's life.
  • D. Šolta
    Šolta is a small Croatian island in the Adriatic Sea, known for its tranquil villages, olive groves, and clear bays, located just off the coast from the city of Split.
  • E. Kehama
    Kehama is the powerful and tyrannical sorcerer-rajah who serves as the central antagonist in Robert Southey’s epic poem "The Curse of Kehama."
  • 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: Maribo
Triple: [Lolland, hasCapital, Maribo]
Generated description
Maribo is a historic market town on the Danish island of Lolland, known for its cathedral and lakeside setting.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maribo
Target entity description: Maribo is a historic market town on the Danish island of Lolland, known for its cathedral and lakeside setting.
  • A. Seskarö
    Seskarö is a Swedish island in the northern Baltic Sea known for its forests, beaches, and traditional fishing and forestry communities.
  • B. Kamarina
    Kamarina is a modern settlement in the Epirus region of northwestern Greece, located near the archaeological site of ancient Cassope.
  • C. Minskov
    Minskov is a supporting character in the French crime drama film "The Beat That My Heart Skipped," involved in the criminal underworld that complicates the protagonist's life.
  • D. Šolta
    Šolta is a small Croatian island in the Adriatic Sea, known for its tranquil villages, olive groves, and clear bays, located just off the coast from the city of Split.
  • E. Kehama
    Kehama is the powerful and tyrannical sorcerer-rajah who serves as the central antagonist in Robert Southey’s epic poem "The Curse of Kehama."
  • 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_69ca83e589948190ac9907819db11ddf completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccc2553e548190898434aeda517407 completed April 1, 2026, 6:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05c0eeb0c8190a5a22c662726805c completed April 4, 2026, 12:32 a.m.
NEDg Description generation batch_69d05cec61908190ae783af982db4170 completed April 4, 2026, 12:35 a.m.
NED2 Entity disambiguation (via description) batch_69d05dbf1ce081908d5c8168a9315942 completed April 4, 2026, 12:39 a.m.
Created at: March 30, 2026, 7:23 p.m.