Triple
T17962626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saranyu |
E449121
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object |
Saranya
Saranya is a variant name of Saranyu, a figure from Hindu mythology associated with the dawn and often regarded as a goddess.
|
E1301714
|
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: Saranya | Statement: [Saranyu, hasAlternativeName, Saranya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saranya Context triple: [Saranyu, hasAlternativeName, Saranya]
-
A.
Bhavatharini
Bhavatharini was an Indian playback singer and music composer known for her work in Tamil cinema and for winning the National Film Award for Best Female Playback Singer.
-
B.
Ramavati
Ramavati was a principal urban center that served as the capital city of the medieval Pala Empire in the Indian subcontinent.
-
C.
Vaidehi
Vaidehi is an epithet of Sita, the revered heroine of the Hindu epic Ramayana and wife of Lord Rama.
-
D.
Naraini
Naraini is a town and administrative subdivision located in the Banda district of Uttar Pradesh, India.
-
E.
Shalini
Shalini is an Indian former film actress best known for her work as a child artist and leading lady in Malayalam and Tamil cinema.
- 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: Saranya Triple: [Saranyu, hasAlternativeName, Saranya]
Generated description
Saranya is a variant name of Saranyu, a figure from Hindu mythology associated with the dawn and often regarded as a goddess.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Saranya Target entity description: Saranya is a variant name of Saranyu, a figure from Hindu mythology associated with the dawn and often regarded as a goddess.
-
A.
Bhavatharini
Bhavatharini was an Indian playback singer and music composer known for her work in Tamil cinema and for winning the National Film Award for Best Female Playback Singer.
-
B.
Ramavati
Ramavati was a principal urban center that served as the capital city of the medieval Pala Empire in the Indian subcontinent.
-
C.
Vaidehi
Vaidehi is an epithet of Sita, the revered heroine of the Hindu epic Ramayana and wife of Lord Rama.
-
D.
Naraini
Naraini is a town and administrative subdivision located in the Banda district of Uttar Pradesh, India.
-
E.
Shalini
Shalini is an Indian former film actress best known for her work as a child artist and leading lady in Malayalam and Tamil cinema.
- 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_69e4b134bc68819097cc199ea8e80f6c |
completed | April 19, 2026, 10:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a034313e1ec8190a2dc15ed8a4cf992 |
completed | May 12, 2026, 3:11 p.m. |
| NEDg | Description generation | batch_6a0345ad1c8c8190bfabd06fcf247862 |
completed | May 12, 2026, 3:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0346008dd881909062ff490df2a721 |
completed | May 12, 2026, 3:23 p.m. |
Created at: April 10, 2026, 10:22 a.m.