Triple

T20654588
Position Surface form Disambiguated ID Type / Status
Subject Kollidam River E507588 entity
Predicate flowsPast P4996 FINISHED
Object Srirangam NE NERFINISHED

How this triple was built (2 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: Srirangam | Statement: [Kollidam River, flowsPast, Srirangam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Srirangam
Context triple: [Kollidam River, flowsPast, Srirangam]
  • A. Srirangam chosen
    Srirangam is a prominent temple town in Tamil Nadu, India, renowned for the vast Sri Ranganathaswamy Temple dedicated to Lord Vishnu.
  • B. Darasuram
    Darasuram is a town in Tamil Nadu, India, renowned for its UNESCO-listed Chola-era Airavatesvara Temple and rich Dravidian architectural heritage.
  • C. Thirunindravur
    Thirunindravur is a suburban town near Chennai in the Indian state of Tamil Nadu, known for its residential growth and historic temples.
  • D. Karpagam
    Karpagam is a notable Indian film associated with the acclaimed actress Savithri, recognized for her impactful performance in it.
  • E. Suchindram
    Suchindram is a temple town in Tamil Nadu, India, renowned for its historic Thanumalayan Temple dedicated to a unique combined form of the Hindu trinity.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4bf58c081908e52a4500e03ff83 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2ec90e881909250884483429acf completed April 20, 2026, 11:12 p.m.
Created at: April 16, 2026, 11:43 a.m.