Triple

T20150645
Position Surface form Disambiguated ID Type / Status
Subject Andhra cuisine E491424 entity
Predicate hasDish P17589 FINISHED
Object ulava charu
Ulava charu is a traditional South Indian lentil-based soup from Andhra Pradesh, made by slow-cooking horse gram and often served with rice or cream.
 E1415225 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: ulava charu | Statement: [Andhra cuisine, hasDish, ulava charu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ulava charu
Context triple: [Andhra cuisine, hasDish, ulava charu]
  • A. Úhlava
    Úhlava is a river in the Czech Republic that flows through the city of Plzeň and is one of the region’s notable waterways.
  • B. Úhlavka
    Úhlavka is a river in the Czech Republic that serves as a tributary of the Mže River.
  • C. Uchali
    Uchali, also known as Uluch Ali, was a prominent 16th-century Ottoman admiral and corsair who rose from captivity to become Kapudan Pasha (grand admiral) of the Ottoman fleet.
  • D. Chára
    Chára is a Slovak surname most prominently associated with Zdeno Chára, the towering NHL defenseman and Stanley Cup champion.
  • E. Uchana
    Uchana is a town in the Jind district of Haryana, India, known as a local administrative and commercial center for the surrounding rural area.
  • 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: ulava charu
Triple: [Andhra cuisine, hasDish, ulava charu]
Generated description
Ulava charu is a traditional South Indian lentil-based soup from Andhra Pradesh, made by slow-cooking horse gram and often served with rice or cream.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ulava charu
Target entity description: Ulava charu is a traditional South Indian lentil-based soup from Andhra Pradesh, made by slow-cooking horse gram and often served with rice or cream.
  • A. Úhlava
    Úhlava is a river in the Czech Republic that flows through the city of Plzeň and is one of the region’s notable waterways.
  • B. Úhlavka
    Úhlavka is a river in the Czech Republic that serves as a tributary of the Mže River.
  • C. Uchali
    Uchali, also known as Uluch Ali, was a prominent 16th-century Ottoman admiral and corsair who rose from captivity to become Kapudan Pasha (grand admiral) of the Ottoman fleet.
  • D. Chára
    Chára is a Slovak surname most prominently associated with Zdeno Chára, the towering NHL defenseman and Stanley Cup champion.
  • E. Uchana
    Uchana is a town in the Jind district of Haryana, India, known as a local administrative and commercial center for the surrounding rural area.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667a1c5848190975b17ab07251f8b completed April 20, 2026, 5:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08346f7b708190b006704558b25a67 completed May 16, 2026, 9:10 a.m.
NEDg Description generation batch_6a08357acba08190be9fcedf1ea0f19d completed May 16, 2026, 9:14 a.m.
NED2 Entity disambiguation (via description) batch_6a0836a5cfdc81908806d83acd257acd completed May 16, 2026, 9:19 a.m.
Created at: April 11, 2026, 11:33 p.m.