Triple
T5706557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Curse of Kehama |
E125796
|
entity |
| Predicate | hasProtagonist |
P8706
|
FINISHED |
| Object | Kailyal |
E539224
|
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: Kailyal | Statement: [The Curse of Kehama, hasProtagonist, Kailyal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kailyal Context triple: [The Curse of Kehama, hasProtagonist, Kailyal]
-
A.
Kailyal
chosen
Kailyal is a central heroine in Robert Southey’s epic poem "The Curse of Kehama," known for her steadfast virtue and endurance amid supernatural trials.
-
B.
Barshaini
Barshaini is a small Himalayan village in Himachal Pradesh, India, that serves as a popular base and trailhead for treks into the Parvati Valley and surrounding high-altitude landscapes.
-
C.
Kadamtala
Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
-
D.
Kasarani
Kasarani is a residential and commercial suburb in northeastern Nairobi, Kenya, known for hosting major sports and educational facilities.
-
E.
Bairat
Bairat is a historic town in Rajasthan, India, known for its ancient Buddhist archaeological remains and connections to the Mauryan period.
- 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_69c0082d6fe48190b777fb383769e5c8 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0248751bc8190b12aaa42d1ef17e3 |
completed | March 22, 2026, 5:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07de7df8c8190824d24f729eaa04d |
completed | March 22, 2026, 11:40 p.m. |
Created at: March 22, 2026, 3:45 p.m.