Triple

T17951281
Position Surface form Disambiguated ID Type / Status
Subject Indrani E448836 entity
Predicate epithet P743 FINISHED
Object Paulomi
Paulomi is another name for the Hindu goddess Indrani, the consort of Indra and queen of the gods in Hindu mythology.
 E1297849 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: Paulomi | Statement: [Indrani, epithet, Paulomi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Paulomi
Context triple: [Indrani, epithet, Paulomi]
  • A. Pia
    Pia is a locality situated near the Agly River in southern France, known for its proximity to this waterway and its Mediterranean regional setting.
  • B. Pia
    Pia is a feminine given name used in various cultures, often derived from Latin meaning "pious" or "devout."
  • C. Rommely
    Rommely is the surname of the fictional Rommely family featured in Betty Smith’s novel "A Tree Grows in Brooklyn."
  • D. Nōmi
    Nōmi was a former town in Hiroshima Prefecture, Japan, that later became part of the city of Etajima through a municipal merger.
  • E. Nozomi
    Nozomi is the fastest and most premium Shinkansen (bullet train) service operating on Japan’s Tokaido and Sanyo lines, known for its high speed and frequent departures between major cities like Tokyo and Osaka.
  • 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: Paulomi
Triple: [Indrani, epithet, Paulomi]
Generated description
Paulomi is another name for the Hindu goddess Indrani, the consort of Indra and queen of the gods in Hindu mythology.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Paulomi
Target entity description: Paulomi is another name for the Hindu goddess Indrani, the consort of Indra and queen of the gods in Hindu mythology.
  • A. Pia
    Pia is a locality situated near the Agly River in southern France, known for its proximity to this waterway and its Mediterranean regional setting.
  • B. Pia
    Pia is a feminine given name used in various cultures, often derived from Latin meaning "pious" or "devout."
  • C. Rommely
    Rommely is the surname of the fictional Rommely family featured in Betty Smith’s novel "A Tree Grows in Brooklyn."
  • D. Nōmi
    Nōmi was a former town in Hiroshima Prefecture, Japan, that later became part of the city of Etajima through a municipal merger.
  • E. Nozomi
    Nozomi is the fastest and most premium Shinkansen (bullet train) service operating on Japan’s Tokaido and Sanyo lines, known for its high speed and frequent departures between major cities like Tokyo and Osaka.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afac95048190a5d1ef012899c62b completed April 19, 2026, 10:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03291e79448190b2e6a8aab9d9f6df completed May 12, 2026, 1:20 p.m.
NEDg Description generation batch_6a032a6fad38819090ccc2cc832f65aa completed May 12, 2026, 1:26 p.m.
NED2 Entity disambiguation (via description) batch_6a032b4c6ed48190bc99ddb9ea7c2ea9 completed May 12, 2026, 1:29 p.m.
Created at: April 10, 2026, 10:21 a.m.