Triple
T36191200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lalitha Devi |
E1046992
|
entity |
| Predicate | hasNameInPalace |
P200156
|
FINISHED |
| Object | Lalitha Mahal |
—
|
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: Lalitha Mahal | Statement: [Lalitha Devi, hasNameInPalace, Lalitha Mahal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNameInPalace Context triple: [Lalitha Devi, hasNameInPalace, Lalitha Mahal]
-
A.
hasCrownName
Indicates that an entity possesses or is identified by a specific crown name, typically used as an official or regal title.
-
B.
hasRoyalNameElement
Indicates that an entity’s name includes a component that is associated with royalty or a royal title.
-
C.
associatedWithPalace
Indicates a relationship where an entity has a connection, link, or involvement with a palace, such as through location, function, ownership, or affiliation.
-
D.
hasRoyalFavourite
Indicates that one entity is the person specially favored or preferred by a royal figure.
-
E.
hasNameInscribed
Indicates that an entity bears another entity’s name physically inscribed on its surface.
- F. None of above. chosen
Provenance (4 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff779e3f0c8190a861f1e4000fd9d9 |
completed | May 9, 2026, 6:06 p.m. |
| PD | Predicate disambiguation | batch_69ff77202638819086e4b9f9c0bc7b31 |
completed | May 9, 2026, 6:04 p.m. |
| PDg | Predicate description generation | batch_69ff779d3d788190af5a2dbc4d7ca3c8 |
completed | May 9, 2026, 6:06 p.m. |
Created at: May 3, 2026, 4:08 p.m.