Triple
T18534271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shikhandi |
E452920
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Amba |
—
|
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: Amba | Statement: [Shikhandi, basedOn, Amba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amba Context triple: [Shikhandi, basedOn, Amba]
-
A.
Amba
chosen
Amba is a tragic princess from the Indian epic Mahabharata, known for her vow of vengeance against Bhishma that ultimately leads to her rebirth as Shikhandi.
-
B.
Amba
Amba is a Hindu goddess, widely revered in western India as a fierce yet protective mother deity often worshipped during Navratri.
-
C.
Amba Alagi
Amba Alagi is a strategically important mountain in northern Ethiopia, historically known as the site of major battles during the Italo-Ethiopian conflicts and World War II.
-
D.
Amara
Amara is a fictional character from the "Creed" film series, known as the daughter of boxer Adonis Creed and musician Bianca Taylor.
-
E.
Adara
Adara is a small coastal village on Atauro Island in East Timor, known for its traditional fishing community and nearby coral reefs popular with divers and snorkelers.
- 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_69d8d387b5548190aa030dad2cb4947e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53400d548819080b17f30b3ee7174 |
completed | April 19, 2026, 7:58 p.m. |
Created at: April 10, 2026, 11:37 a.m.