Triple

T9189105
Position Surface form Disambiguated ID Type / Status
Subject Pisz E220534 entity
Predicate hasLandmark P105 FINISHED
Object Pisz marina
Pisz marina is a small harbor and recreational boating facility in the town of Pisz, serving as a gateway to the Masurian Lakes in northeastern Poland.
 E220534 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: Pisz marina | Statement: [Pisz, hasLandmark, Pisz marina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pisz marina
Context triple: [Pisz, hasLandmark, Pisz marina]
  • A. Pisz
    Pisz is a town in northeastern Poland known for its location in the Masurian Lake District and proximity to extensive forests and lakes.
  • B. Marina Lu
    Marina Lu is the mother of renowned cellist Yo-Yo Ma.
  • C. Marina Piran
    Marina Piran is a marina and small harbor facility serving the coastal town of Piran in southwestern Slovenia, providing berths and services for recreational and smaller commercial vessels.
  • 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. Dar Pomorza
    Dar Pomorza is a historic Polish sailing frigate, now preserved as a museum ship and popular tourist attraction in Gdynia.
  • 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: Pisz marina
Triple: [Pisz, hasLandmark, Pisz marina]
Generated description
Pisz marina is a small harbor and recreational boating facility in the town of Pisz, serving as a gateway to the Masurian Lakes in northeastern Poland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pisz marina
Target entity description: Pisz marina is a small harbor and recreational boating facility in the town of Pisz, serving as a gateway to the Masurian Lakes in northeastern Poland.
  • A. Pisz chosen
    Pisz is a town in northeastern Poland known for its location in the Masurian Lake District and proximity to extensive forests and lakes.
  • B. Marina Lu
    Marina Lu is the mother of renowned cellist Yo-Yo Ma.
  • C. Marina Piran
    Marina Piran is a marina and small harbor facility serving the coastal town of Piran in southwestern Slovenia, providing berths and services for recreational and smaller commercial vessels.
  • 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. Dar Pomorza
    Dar Pomorza is a historic Polish sailing frigate, now preserved as a museum ship and popular tourist attraction in Gdynia.
  • F. None of above.

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_69ca83e6d77c81909862b7afef56b1bf completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd5bd8c5c81909d0cdbcd7410fcee completed April 1, 2026, 8:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05c272f508190aade1769c88cf16d completed April 4, 2026, 12:32 a.m.
NEDg Description generation batch_69d05cda59f88190bcde5a91aec2f9dd completed April 4, 2026, 12:35 a.m.
NED2 Entity disambiguation (via description) batch_69d05ddd28008190b82c42220871e73f completed April 4, 2026, 12:39 a.m.
Created at: March 30, 2026, 7:24 p.m.