Triple

T14082819
Position Surface form Disambiguated ID Type / Status
Subject Litunga E338908 entity
Predicate traditionalCourt P112740 FINISHED
Object Kuta E132180 NE FINISHED

How this triple was built (3 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: Kuta | Statement: [Litunga, traditionalCourt, Kuta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kuta
Context triple: [Litunga, traditionalCourt, Kuta]
  • A. Kuta chosen
    Kuta is a popular beach resort town in southern Bali, Indonesia, known for its surfing waves, vibrant nightlife, and dense concentration of hotels, shops, and restaurants.
  • B. Kut
    Kut is a city in eastern Iraq situated on the banks of the Tigris River, known historically as a strategic location and the site of significant World War I battles.
  • C. Kuto
    Kuto is a neighborhood and urban district within the city of Abeokuta in Ogun State, southwestern Nigeria.
  • D. Kōta
    Kōta is a town in central Japan known for its manufacturing industries and location within Aichi Prefecture.
  • E. Kutaisi
    Kutaisi is one of Georgia’s major cities, historically significant and formerly a capital, located in the western part of the country.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: traditionalCourt
Context triple: [Litunga, traditionalCourt, Kuta]
  • A. trialCourt
    Indicates that a legal matter, decision, or proceeding is associated with, handled by, or occurring in a court of first instance (the trial-level court).
  • B. courtStyle
    Indicates the manner or stylistic approach in which a court conducts its proceedings or presents its decisions.
  • C. usedCourt
    Indicates that an entity made use of or participated in legal proceedings within a particular court.
  • D. parallelCourt
    Indicates that two legal proceedings or courts are operating at the same time on related or comparable matters, without one being hierarchically superior to the other.
  • E. courtContext
    Indicates the legal or judicial setting, circumstances, or framework within which a court-related action or relationship takes place.
  • 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_69d81c687b0c819087fd9ed4198403f8 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5ede40048190b465e909565730c1 completed April 14, 2026, 3:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb6749c3c81909833a0b6ddcae3fb completed May 7, 2026, 3:57 p.m.
PD Predicate disambiguation batch_69de05b0e6c88190a819eeba0028981f completed April 14, 2026, 9:15 a.m.
PDg Predicate description generation batch_69de2398856c81908bed6070e4ca6ab1 completed April 14, 2026, 11:23 a.m.
Created at: April 9, 2026, 10:21 p.m.