Triple
T4882361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Devi Mahatmya |
E109358
|
entity |
| Predicate | thirdEpisode |
P59591
|
FINISHED |
| Object | slaying of Shumbha and Nishumbha |
—
|
LITERAL 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: slaying of Shumbha and Nishumbha | Statement: [Devi Mahatmya, thirdEpisode, slaying of Shumbha and Nishumbha]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thirdEpisode Context triple: [Devi Mahatmya, thirdEpisode, slaying of Shumbha and Nishumbha]
-
A.
thirdFilm
Indicates that one film is the third installment or entry in a sequence or series relative to another film.
-
B.
thirdWord
Indicates that one entity is the third word in sequence within another entity (such as a text or phrase).
-
C.
thirdSingle
Indicates that an entity is the third single (e.g., third single release) associated with another entity, typically in a sequence such as from an album or artist.
-
D.
thirdTemptation
Indicates the relationship in which an entity is subjected to or involved in the third in a sequence of temptations or tests.
-
E.
thirdSeasonBasedOn
Indicates that the third season of a work is adapted from or derived from another source material.
- 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_69bd440e9d64819083e82cf33b4d9570 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ddfff0c81908fb148a6f6508334 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69bd6d5976a081909090c0c263f6e9b7 |
completed | March 20, 2026, 3:52 p.m. |
Created at: March 20, 2026, 1:27 p.m.