Triple

T21108393
Position Surface form Disambiguated ID Type / Status
Subject Sassi E520111 entity
Predicate partner P1136 FINISHED
Object Punnun 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: Punnun | Statement: [Sassi, partner, Punnun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Punnun
Context triple: [Sassi, partner, Punnun]
  • A. Punnun chosen
    Punnun is a legendary prince and tragic lover from the Sindhi and Balochi folktale "Sassi Punnun," renowned for his doomed romance with Sassi.
  • B. Punia
    Punia is a town and administrative center located in Maniema Province in the eastern part of the Democratic Republic of the Congo.
  • C. Punhete
    Punhete is the former name of the Portuguese town and municipality now known as Constância, located at the confluence of the Zêzere and Tagus rivers in central Portugal.
  • D. Punilla
    Punilla is a province in Chile’s Ñuble Region, known for its predominantly rural character and agricultural activities.
  • E. Punhana
    Punhana is a prominent town in Haryana, India, known as one of the key urban centers of Nuh district.
  • 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_69e0b509a318819092fbbcb21d1fe603 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e720ffa998819082db225363ac3b23 completed April 21, 2026, 7:02 a.m.
Created at: April 16, 2026, 2:54 p.m.