Triple
T13774382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Panguni Uttiram |
E330963
|
entity |
| Predicate | associatedWithDeity |
P1481
|
FINISHED |
| Object | Valli |
E161607
|
NE FINISHED |
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: Valli | Statement: [Panguni Uttiram, associatedWithDeity, Valli]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Valli Context triple: [Panguni Uttiram, associatedWithDeity, Valli]
-
A.
Valli
Valli is the professional name of Alida Valli, an acclaimed Italian actress known for her roles in classic European and Hollywood films.
-
B.
Valli
chosen
Valli is a Hindu goddess and one of the two principal consorts of the god Kartikeya (Murugan), especially revered in South Indian and Tamil traditions.
-
C.
Anandamoyi
Anandamoyi is a central character in Rabindranath Tagore’s novel "Gora," known for her deep spirituality, maternal compassion, and pivotal influence on the protagonist’s moral and religious awakening.
-
D.
Ruka Pillan
Ruka Pillan is a highly active stratovolcano in southern Chile, renowned for its frequent eruptions and significance in Mapuche mythology.
-
E.
Nabaneeta
Nabaneeta is a feminine given name most notably borne by the acclaimed Indian Bengali writer and academic Nabaneeta Dev Sen.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d81c583b0081909e408a17db517a21 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de023774b48190b19e43e87b94ba77 |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7a86afd788190ab637044dd489a24 |
completed | May 3, 2026, 7:56 p.m. |
Created at: April 9, 2026, 10:10 p.m.