Triple

T2525857
Position Surface form Disambiguated ID Type / Status
Subject Upper Burma E56032 entity
Predicate historicalCapital P2536 FINISHED
Object Ava
Ava was a prominent historical city and royal capital in Upper Burma (now Myanmar), serving as a major political and cultural center for several Burmese kingdoms.
 E276019 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: Ava | Statement: [Upper Burma, historicalCapital, Ava]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ava
Context triple: [Upper Burma, historicalCapital, Ava]
  • A. Ava
    Ava is a feminine given name most famously associated with American actress and Hollywood icon Ava Gardner.
  • B. Arielle
    Arielle is a given name shared by various individuals, including Arielle Zuckerberg, a venture capitalist and younger sister of Meta co-founder Mark Zuckerberg.
  • C. Lena
    Lena is a common feminine given name used in many languages, often derived from longer names such as Magdalena or Helena.
  • D. Lena
    Lena is an alternate given name of Lee Krasner, the influential American abstract expressionist painter and wife of Jackson Pollock.
  • E. Emmie
    Emmie is a diminutive given name, typically used as a affectionate or informal variant of names like Emma.
  • 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: Ava
Triple: [Upper Burma, historicalCapital, Ava]
Generated description
Ava was a prominent historical city and royal capital in Upper Burma (now Myanmar), serving as a major political and cultural center for several Burmese kingdoms.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ava
Target entity description: Ava was a prominent historical city and royal capital in Upper Burma (now Myanmar), serving as a major political and cultural center for several Burmese kingdoms.
  • A. Ava
    Ava is a feminine given name most famously associated with American actress and Hollywood icon Ava Gardner.
  • B. Arielle
    Arielle is a given name shared by various individuals, including Arielle Zuckerberg, a venture capitalist and younger sister of Meta co-founder Mark Zuckerberg.
  • C. Lena
    Lena is an alternate given name of Lee Krasner, the influential American abstract expressionist painter and wife of Jackson Pollock.
  • D. Lena
    Lena is a common feminine given name used in many languages, often derived from longer names such as Magdalena or Helena.
  • E. Emmie
    Emmie is a diminutive given name, typically used as a affectionate or informal variant of names like Emma.
  • 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_69ab4a48e4f081908f1218d244608659 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd2544b4481908e105294cebdbb1f completed March 7, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69af2bb0658c8190b71e1352dc4f6be3 completed March 9, 2026, 8:21 p.m.
NEDg Description generation batch_69af551d68448190a076e659be28b891 completed March 9, 2026, 11:17 p.m.
NED2 Entity disambiguation (via description) batch_69af560837388190b082a8f1bee36c51 completed March 9, 2026, 11:21 p.m.
Created at: March 6, 2026, 9:46 p.m.