Triple
T3369508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rajputs |
E70918
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Raja |
E310655
|
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: Raja | Statement: [Rajputs, title, Raja]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Raja Context triple: [Rajputs, title, Raja]
-
A.
Raja
chosen
Raja is a traditional Indian royal title historically used by Hindu monarchs and regional rulers.
-
B.
Maharaja
Maharaja is a royal title historically used by sovereign Hindu and Sikh rulers in the Indian subcontinent, denoting a "great king" or high-ranking monarch.
-
C.
Rajasbai
Rajasbai was a queen consort of the Maratha Empire, known primarily as one of the wives of Chhatrapati Rajaram I.
-
D.
Raj
Raj is the given name of Raj Reddy, a pioneering computer scientist known for his foundational work in artificial intelligence and robotics.
-
E.
Pavanputra
Pavanputra is a revered epithet of the Hindu deity Hanuman, highlighting his divine parentage as the son of the wind god.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2b9b1fc8190a2cbf040ea808baf |
completed | March 8, 2026, 5:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b334396f588190add5c0c27949650c |
completed | March 12, 2026, 9:46 p.m. |
Created at: March 8, 2026, 3:13 p.m.