Triple
T36890296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chalukya of Kalyani |
E911728
|
entity |
| Predicate | mostPowerfulRuler |
P147952
|
FINISHED |
| Object | Vikramaditya VI |
—
|
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: Vikramaditya VI | Statement: [Chalukya of Kalyani, mostPowerfulRuler, Vikramaditya VI]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mostPowerfulRuler Context triple: [Chalukya of Kalyani, mostPowerfulRuler, Vikramaditya VI]
-
A.
mostPowerfulKing
Indicates that the subject is the king who holds the greatest power or authority among a specified group of kings.
-
B.
historicalRulers
Indicates that one entity has served as a ruler or governing authority over the other entity at some point in history.
-
C.
associatedDynastyRuler
chosen
Indicates a relationship where a dynasty is linked to the ruler who governed or is historically connected with it.
-
D.
recognizedAsRulersBy
Indicates that certain entities are acknowledged or accepted by others as their legitimate rulers or authorities.
-
E.
hasFamousRuler
Indicates that an entity is or was ruled by a ruler who is widely recognized or historically notable.
- F. None of above.
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_69f76e8335908190b77e7e11d0e80820 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd89df408190a2e78c3a93eb9ed8 |
completed | May 5, 2026, 2:24 p.m. |
| PD | Predicate disambiguation | batch_69f7cf79ddb08190a083405cccc14137 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:13 p.m.