Triple

T15870806
Position Surface form Disambiguated ID Type / Status
Subject Poso E384823 entity
Predicate connectedByRoadTo P11435 FINISHED
Object Tentena
Tentena is a small lakeside town in Central Sulawesi, Indonesia, known as a gateway to Lake Poso and the surrounding highland scenery.
 E1181282 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: Tentena | Statement: [Poso, connectedByRoadTo, Tentena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tentena
Context triple: [Poso, connectedByRoadTo, Tentena]
  • A. Tentyra
    Tentyra is the Greek name for the ancient Egyptian town of Iunet (modern Dendera), renowned for its temple complex dedicated to the goddess Hathor.
  • B. Tantolunden
    Tantolunden is a large park and recreational area in Stockholm known for its allotment gardens, waterfront, and outdoor activities.
  • C. Taborio
    Taborio is a village settlement located on the island of Nonouti in the Republic of Kiribati.
  • D. Tadoe
    Tadoe is an American rapper from Chicago known for his involvement in the drill music scene and frequent collaborations with artists like Chief Keef and Young Chop.
  • E. Torentje
    Torentje is the small historic tower in The Hague that serves as the Dutch Prime Minister’s official office.
  • 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: Tentena
Triple: [Poso, connectedByRoadTo, Tentena]
Generated description
Tentena is a small lakeside town in Central Sulawesi, Indonesia, known as a gateway to Lake Poso and the surrounding highland scenery.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tentena
Target entity description: Tentena is a small lakeside town in Central Sulawesi, Indonesia, known as a gateway to Lake Poso and the surrounding highland scenery.
  • A. Tentyra
    Tentyra is the Greek name for the ancient Egyptian town of Iunet (modern Dendera), renowned for its temple complex dedicated to the goddess Hathor.
  • B. Tantolunden
    Tantolunden is a large park and recreational area in Stockholm known for its allotment gardens, waterfront, and outdoor activities.
  • C. Taborio
    Taborio is a village settlement located on the island of Nonouti in the Republic of Kiribati.
  • D. Tadoe
    Tadoe is an American rapper from Chicago known for his involvement in the drill music scene and frequent collaborations with artists like Chief Keef and Young Chop.
  • E. Torentje
    Torentje is the small historic tower in The Hague that serves as the Dutch Prime Minister’s official office.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155f915788190a8efc3b3380cb829 completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa94ca15c8190bdd5fe0a30b54b51 completed May 9, 2026, 9:38 p.m.
NEDg Description generation batch_69ffaa3903408190b7beaa6b461bd2bd completed May 9, 2026, 9:42 p.m.
NED2 Entity disambiguation (via description) batch_69ffab0c79d4819085f0ed6a4edcb7fb completed May 9, 2026, 9:45 p.m.
Created at: April 10, 2026, 4:50 a.m.