Triple
T22508717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lavan (Sikh marriage hymns) |
E556458
|
entity |
| Predicate | secondVerseFocus |
P48412
|
FINISHED |
| Object | deepening love and devotion |
—
|
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: deepening love and devotion | Statement: [Lavan (Sikh marriage hymns), secondVerseFocus, deepening love and devotion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondVerseFocus Context triple: [Lavan (Sikh marriage hymns), secondVerseFocus, deepening love and devotion]
-
A.
secondPartFocus
Indicates that the communicative or informational focus is placed on the second part or element in a two-part structure or relation.
-
B.
secondEditionFocus
Indicates that the relationship or content specifically pertains to the second edition version or focus of something, as opposed to other editions.
-
C.
verse2
chosen
Indicates that one entity is the second verse or stanza associated with another entity, typically within a structured text like a song, poem, or scripture.
-
D.
secondSpeechFocus
Indicates that the second mentioned speech segment or utterance is the primary focus or target of attention in the described context.
-
E.
secondWord
Indicates that one entity is the second word in sequence immediately following the first entity in a text or utterance.
- 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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15d5ebe5881908a22d519128415f2 |
completed | April 29, 2026, 1:22 a.m. |
| PD | Predicate disambiguation | batch_69e898be31448190be5ae7f5656f0497 |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:50 p.m.