Triple

T22458762
Position Surface form Disambiguated ID Type / Status
Subject Kerala cuisine E555178 entity
Predicate usesIngredient P12771 FINISHED
Object tapioca
Tapioca is a starchy food product made from the cassava root, commonly used worldwide in dishes like puddings, flatbreads, and snack foods.
 E1537776 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: tapioca | Statement: [Kerala cuisine, usesIngredient, tapioca]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: tapioca
Context triple: [Kerala cuisine, usesIngredient, tapioca]
  • A. Harinas
    Harinas is a rural settlement located within Syangja District in the Gandaki Province of central Nepal.
  • B. Taro
    Taro is a common Japanese male given name, often written with kanji meaning "eldest son" or similar traditional connotations.
  • C. Taro
    The Taro is a river in northern Italy that flows through the Emilia-Romagna region and ultimately joins the Po River.
  • D. Yam
    Yam is the ancient Canaanite and Phoenician god of the sea, often depicted as a primordial chaos deity and rival of the storm god Baal.
  • E. Yam
    Yam is a Cantonese romanization of the Chinese surname Yan, commonly used among Cantonese-speaking communities.
  • 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: tapioca
Triple: [Kerala cuisine, usesIngredient, tapioca]
Generated description
Tapioca is a starchy food product made from the cassava root, commonly used worldwide in dishes like puddings, flatbreads, and snack foods.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: tapioca
Target entity description: Tapioca is a starchy food product made from the cassava root, commonly used worldwide in dishes like puddings, flatbreads, and snack foods.
  • A. Harinas
    Harinas is a rural settlement located within Syangja District in the Gandaki Province of central Nepal.
  • B. Taro
    Taro is a common Japanese male given name, often written with kanji meaning "eldest son" or similar traditional connotations.
  • C. Taro
    The Taro is a river in northern Italy that flows through the Emilia-Romagna region and ultimately joins the Po River.
  • D. Yam
    Yam is the ancient Canaanite and Phoenician god of the sea, often depicted as a primordial chaos deity and rival of the storm god Baal.
  • E. Yam
    Yam is a Cantonese romanization of the Chinese surname Yan, commonly used among Cantonese-speaking communities.
  • 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_69e11e51fdec8190adfdf9f8a6362221 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b7e01fc8190825c3dc024484440 completed April 29, 2026, 1:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b0c8217ac8190af16df3d941446ce completed May 18, 2026, 12:56 p.m.
NEDg Description generation batch_6a0b0d1e3ba08190bf963526973cd462 completed May 18, 2026, 12:59 p.m.
NED2 Entity disambiguation (via description) batch_6a0b0dc247b88190b8c54084c5727941 completed May 18, 2026, 1:01 p.m.
Created at: April 16, 2026, 8:48 p.m.