Triple
T10311847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tharu |
E241909
|
entity |
| Predicate | hasFestival |
P3113
|
FINISHED |
| Object | Maghi |
E114662
|
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: Maghi | Statement: [Tharu, hasFestival, Maghi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maghi Context triple: [Tharu, hasFestival, Maghi]
-
A.
Maghi
chosen
Maghi is a regional name for the Hindu harvest festival of Makar Sankranti, particularly observed in parts of North India.
-
B.
Maghnia
Maghnia is a town in northwestern Algeria near the Moroccan border, known as the birthplace of Algeria’s first president, Ahmed Ben Bella.
-
C.
Dhulandi
Dhulandi is the vibrant second day of the Holi festival in India, celebrated with the playful throwing of colored powders and water.
-
D.
Mazarati
Mazarati was a mid-1980s funk and R&B band from the Prince-associated Minneapolis music scene, best known for their connection to The Revolution’s BrownMark and the original version of “Kiss.”
-
E.
Mahraganat
Mahraganat is a contemporary Egyptian street music genre that blends electronic beats, folk influences, and socially charged lyrics, often associated with youth culture and urban celebrations.
- 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_69d381ac38808190a8ca7457c85b625b |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d32b85288190a11e09a0ab80d66c |
completed | April 7, 2026, 9:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71d801978819097293b5c98350fef |
completed | April 9, 2026, 3:31 a.m. |
Created at: April 6, 2026, 11:48 a.m.