Triple
T24696879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brahma-vamsa |
E611614
|
entity |
| Predicate | tracedThrough |
P11414
|
FINISHED |
| Object | Marichi |
—
|
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: Marichi | Statement: [Brahma-vamsa, tracedThrough, Marichi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tracedThrough Context triple: [Brahma-vamsa, tracedThrough, Marichi]
-
A.
traceOf
Indicates that one entity is a remaining sign, mark, or residual evidence of the presence, existence, or action of another entity.
-
B.
tracesTo
chosen
Indicates a relationship where one item can be followed or linked back as the origin, source, or cause of another.
-
C.
trace
Indicates following or mapping the path, origin, or development of something step by step through evidence or markers.
-
D.
traceWithRespectTo
Indicates that one entity records, follows, or monitors the behavior, changes, or effects of another entity relative to a specified reference or context.
-
E.
trackedOn
Indicates that the subject’s status, activity, or changes are being monitored or recorded on the specified system, platform, or medium.
- 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_69e2c4d76d148190b58ad612467149a5 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f410fe3b848190ae296a29f742ee30 |
completed | May 1, 2026, 2:33 a.m. |
| PD | Predicate disambiguation | batch_69f40ee8ada8819089a7016b50308ff0 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 3:22 a.m.