Triple

T23973277
Position Surface form Disambiguated ID Type / Status
Subject Tam Coc caves E604292 entity
Predicate contains P35 FINISHED
Object Hang Hai cave
Hang Hai cave is one of the scenic limestone caves within the Tam Coc cave system in Ninh Binh, Vietnam, known for its karst formations and boat-accessible passages along the Ngo Dong River.
E1613988 NE FINISHED

How this triple was built (2 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: Hang Hai cave | Statement: [Tam Coc caves, contains, Hang Hai cave]
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: Hang Hai cave
Triple: [Tam Coc caves, contains, Hang Hai cave]
Generated description
Hang Hai cave is one of the scenic limestone caves within the Tam Coc cave system in Ninh Binh, Vietnam, known for its karst formations and boat-accessible passages along the Ngo Dong River.

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_69e29543019c8190872462e593cc50b4 completed April 17, 2026, 8:17 p.m.
NER Named-entity recognition batch_69f1d1dda91c8190af716bceb3225aee completed April 29, 2026, 9:39 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f963f887081908c14b05fa1c9ed32 completed May 21, 2026, 11:33 p.m.
NEDg Description generation batch_6a0f9802d1bc8190b3f47810e29ef246 completed May 21, 2026, 11:40 p.m.
NED2 Entity disambiguation (via description) batch_6a0f992af65c819085d30795965384cb completed May 21, 2026, 11:45 p.m.
Created at: April 17, 2026, 9:25 p.m.