Triple

T13016481
Position Surface form Disambiguated ID Type / Status
Subject Trapaceae E322564 entity
Predicate hasTypeGenus P5980 FINISHED
Object Trapa
Trapa is a genus of aquatic plants commonly known as water chestnuts, characterized by floating rosettes of leaves and spiny, edible fruits.
E1016491 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: Trapa | Statement: [Trapaceae, hasTypeGenus, Trapa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trapa
Context triple: [Trapaceae, hasTypeGenus, Trapa]
  • A. Balitora
    Balitora is a genus of small, bottom-dwelling freshwater fishes commonly known as stone loaches, found in fast-flowing streams of South and Southeast Asia.
  • B. Parchal
    Parchal is a town in Portugal’s Algarve region, situated near the Arade River opposite Portimão and known historically for its fishing and canning industries.
  • C. Banjara
    Banjara are a traditionally nomadic tribal community of India known for their vibrant attire, folk traditions, and history as traders and transporters.
  • D. Bhailsa
    Bhailsa is the former historical name of Vidisha, an ancient city in the central Indian state of Madhya Pradesh known for its rich archaeological and cultural heritage.
  • E. Sawndip
    Sawndip is the traditional logographic script used for writing the Zhuang language, based largely on adapted Chinese characters.
  • 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: Trapa
Triple: [Trapaceae, hasTypeGenus, Trapa]
Generated description
Trapa is a genus of aquatic plants commonly known as water chestnuts, characterized by floating rosettes of leaves and spiny, edible fruits.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Trapa
Target entity description: Trapa is a genus of aquatic plants commonly known as water chestnuts, characterized by floating rosettes of leaves and spiny, edible fruits.
  • A. Balitora
    Balitora is a genus of small, bottom-dwelling freshwater fishes commonly known as stone loaches, found in fast-flowing streams of South and Southeast Asia.
  • B. Parchal
    Parchal is a town in Portugal’s Algarve region, situated near the Arade River opposite Portimão and known historically for its fishing and canning industries.
  • C. Banjara
    Banjara are a traditionally nomadic tribal community of India known for their vibrant attire, folk traditions, and history as traders and transporters.
  • D. Bhailsa
    Bhailsa is the former historical name of Vidisha, an ancient city in the central Indian state of Madhya Pradesh known for its rich archaeological and cultural heritage.
  • E. Sawndip
    Sawndip is the traditional logographic script used for writing the Zhuang language, based largely on adapted Chinese characters.
  • 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_69d807657e8c8190bd9435ee2f823845 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97ecd04748190ade2530ee5db35fe completed April 10, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c1147974819090007c21383d5c86 completed May 3, 2026, 3:29 a.m.
NEDg Description generation batch_69f6c562d10c8190b76dbf50a0101bae completed May 3, 2026, 3:47 a.m.
NED2 Entity disambiguation (via description) batch_69f6c63762ac8190957c2e4992aa94fd completed May 3, 2026, 3:51 a.m.
Created at: April 9, 2026, 8:51 p.m.