Triple
T27431971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madhusudan Dutt |
E690665
|
entity |
| Predicate | usedVerseForm |
P6967
|
FINISHED |
| Object | blank verse in Bengali poetry |
—
|
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: blank verse in Bengali poetry | Statement: [Madhusudan Dutt, usedVerseForm, blank verse in Bengali poetry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedVerseForm Context triple: [Madhusudan Dutt, usedVerseForm, blank verse in Bengali poetry]
-
A.
verseForm
chosen
Indicates the specific structural or metrical pattern in which a verse or poem is composed.
-
B.
verses
Indicates a relationship where one entity competes or is pitted against another, as in an opposition, matchup, or comparison.
-
C.
verse
Indicates that one entity is in opposition or conflict against another, as in a competitive or adversarial relationship.
-
D.
usedInSpokenForm
Indicates that something (such as a word, name, or expression) is employed in spoken language or oral communication.
-
E.
isConjugatedTo
Indicates that two verb forms are related as different inflectional variants of the same verb through conjugation.
- 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_69ef52003fb48190b0f1295246182a86 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62d5ae2f481909ab113c257e75f9c |
completed | May 2, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 12:42 p.m.