Triple

T7862380
Position Surface form Disambiguated ID Type / Status
Subject Royal Manas National Park E182528 entity
Predicate hasRiver P165 FINISHED
Object Mangdechhu
Mangdechhu is a river in Bhutan known for flowing through ecologically rich protected areas and hosting major hydropower projects.
 E695891 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: Mangdechhu | Statement: [Royal Manas National Park, hasRiver, Mangdechhu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mangdechhu
Context triple: [Royal Manas National Park, hasRiver, Mangdechhu]
  • A. Sairang
    Sairang is a small town in the Indian state of Mizoram, known for its scenic riverside setting and role as a transport and trading hub near the state capital Aizawl.
  • B. Tillangchong
    Tillangchong is a remote, sparsely inhabited island in India’s Nicobar archipelago, noted for its dense tropical forests and rich marine and bird life.
  • C. Mongpan
    Mongpan is a historic Shan principality in what is now Myanmar, known as one of the traditional Shan States.
  • D. Dhom Dam
    Dhom Dam is a major masonry dam in Maharashtra, India, built on the Krishna River to provide irrigation, drinking water, and hydroelectric power.
  • E. Kattang
    Kattang is an Aboriginal Australian language traditionally spoken by the Worimi people of New South Wales.
  • 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: Mangdechhu
Triple: [Royal Manas National Park, hasRiver, Mangdechhu]
Generated description
Mangdechhu is a river in Bhutan known for flowing through ecologically rich protected areas and hosting major hydropower projects.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mangdechhu
Target entity description: Mangdechhu is a river in Bhutan known for flowing through ecologically rich protected areas and hosting major hydropower projects.
  • A. Sairang
    Sairang is a small town in the Indian state of Mizoram, known for its scenic riverside setting and role as a transport and trading hub near the state capital Aizawl.
  • B. Tillangchong
    Tillangchong is a remote, sparsely inhabited island in India’s Nicobar archipelago, noted for its dense tropical forests and rich marine and bird life.
  • C. Mongpan
    Mongpan is a historic Shan principality in what is now Myanmar, known as one of the traditional Shan States.
  • D. Dhom Dam
    Dhom Dam is a major masonry dam in Maharashtra, India, built on the Krishna River to provide irrigation, drinking water, and hydroelectric power.
  • E. Kattang
    Kattang is an Aboriginal Australian language traditionally spoken by the Worimi people of New South Wales.
  • 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_69ca82887fd48190975896bf38c4596b completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb36be5f408190b82a097b0825c57a completed March 31, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5b49a7288190ae6758647fb35ac9 completed March 31, 2026, 5:27 a.m.
NEDg Description generation batch_69cb5f1c9ef08190b1b79482f39966c7 completed March 31, 2026, 5:43 a.m.
NED2 Entity disambiguation (via description) batch_69cb767b198481909cfc1f7a44e6f0d8 completed March 31, 2026, 7:23 a.m.
Created at: March 30, 2026, 4:53 p.m.