Triple

T35019547
Position Surface form Disambiguated ID Type / Status
Subject Akaka Falls State Park E1010155 entity
Predicate hasSecondaryWaterfall P13549 FINISHED
Object Kahuna Falls
Kahuna Falls is a lesser-known but scenic waterfall on Hawaii’s Big Island, located within the lush rainforest setting of Akaka Falls State Park.
 E2123829 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: Kahuna Falls | Statement: [Akaka Falls State Park, hasSecondaryWaterfall, Kahuna Falls]
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: Kahuna Falls
Triple: [Akaka Falls State Park, hasSecondaryWaterfall, Kahuna Falls]
Generated description
Kahuna Falls is a lesser-known but scenic waterfall on Hawaii’s Big Island, located within the lush rainforest setting of Akaka Falls State Park.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasSecondaryWaterfall
Context triple: [Akaka Falls State Park, hasSecondaryWaterfall, Kahuna Falls]
  • A. hasWaterfall chosen
    Indicates that one entity possesses, contains, or features a waterfall associated with it.
  • B. hasWaterfallType
    Indicates that one entity is characterized by or associated with a specific type or classification of waterfall.
  • C. hasSecondary
    Indicates that an entity is associated with an additional or subordinate counterpart beyond its primary one.
  • D. hasSecondarySee
    Indicates that an entity has an additional, secondary “see also” reference or cross-link to another related entity.
  • E. hasSecondaryComponent
    Indicates that an entity includes or is associated with an additional, subordinate component beyond its primary one.
  • F. None of above.

Provenance (6 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_69f76dcc3ac8819096a3ed52f5fa2523 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69fffc783b648190bcd7df017514d206 completed May 10, 2026, 3:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a37c62b4cc08190a2822971755e55e4 completed June 21, 2026, 11:08 a.m.
NEDg Description generation batch_6a37c7187c388190ab55208207921fca completed June 21, 2026, 11:12 a.m.
NED2 Entity disambiguation (via description) batch_6a37c7b73ae8819098cd954a7ef91e4b completed June 21, 2026, 11:15 a.m.
PD Predicate disambiguation batch_69fffc03fa24819099e12413dc6e0afd completed May 10, 2026, 3:31 a.m.
Created at: May 3, 2026, 4:01 p.m.