Triple

T11122475
Position Surface form Disambiguated ID Type / Status
Subject Kadamba dynasty E263050 entity
Predicate hasMonarch P765 FINISHED
Object Kangavarma
Kangavarma was an early ruler of the Kadamba dynasty in ancient Karnataka, known for consolidating the kingdom’s power and territorial control.
E906101 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: Kangavarma | Statement: [Kadamba dynasty, hasMonarch, Kangavarma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kangavarma
Context triple: [Kadamba dynasty, hasMonarch, Kangavarma]
  • A. Varma
    Varma is a surname of Indian origin borne by numerous notable individuals across fields such as politics, arts, and entertainment.
  • B. Kagermeer
    Kagermeer is a lake in the Kagerplassen lake district in South Holland, Netherlands, popular for boating and watersports.
  • C. Isokyrö
    Isokyrö is a rural municipality in western Finland known for its historic churches, agricultural landscape, and traditional Ostrobothnian culture.
  • D. Hotien
    Hotien is an alternative romanized spelling of Hotan, a historic oasis city in southwestern Xinjiang, China, known for its ancient Silk Road heritage and jade production.
  • E. Klakah
    Klakah is a town in East Java, Indonesia, situated close to Mount Lamongan and known for its surrounding volcanic lakes and agricultural landscape.
  • 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: Kangavarma
Triple: [Kadamba dynasty, hasMonarch, Kangavarma]
Generated description
Kangavarma was an early ruler of the Kadamba dynasty in ancient Karnataka, known for consolidating the kingdom’s power and territorial control.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kangavarma
Target entity description: Kangavarma was an early ruler of the Kadamba dynasty in ancient Karnataka, known for consolidating the kingdom’s power and territorial control.
  • A. Varma
    Varma is a surname of Indian origin borne by numerous notable individuals across fields such as politics, arts, and entertainment.
  • B. Kagermeer
    Kagermeer is a lake in the Kagerplassen lake district in South Holland, Netherlands, popular for boating and watersports.
  • C. Isokyrö
    Isokyrö is a rural municipality in western Finland known for its historic churches, agricultural landscape, and traditional Ostrobothnian culture.
  • D. Hotien
    Hotien is an alternative romanized spelling of Hotan, a historic oasis city in southwestern Xinjiang, China, known for its ancient Silk Road heritage and jade production.
  • E. Klakah
    Klakah is a town in East Java, Indonesia, situated close to Mount Lamongan and known for its surrounding volcanic lakes and agricultural landscape.
  • 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_69d6aa9b46cc8190b19f9f0cc45bf322 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79afa0ab88190ab6d61df8cf485ec completed April 9, 2026, 12:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69e42d8643748190a7801fc401dd2b5a completed April 19, 2026, 1:19 a.m.
NEDg Description generation batch_69e42f3eaa0c819095e5af20b910d979 completed April 19, 2026, 1:26 a.m.
NED2 Entity disambiguation (via description) batch_69e43771eaec8190be9bb709723931e0 completed April 19, 2026, 2:01 a.m.
Created at: April 8, 2026, 9:28 p.m.