Triple
T12788489
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chaitra |
E305693
|
entity |
| Predicate | hasBeginningDefinedBy |
P58342
|
FINISHED |
| Object | new moon |
—
|
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: new moon | Statement: [Chaitra, hasBeginningDefinedBy, new moon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBeginningDefinedBy Context triple: [Chaitra, hasBeginningDefinedBy, new moon]
-
A.
hasNoBeginningOrEnd
Indicates that the related entity exists without a starting point or ending point in time or extent.
-
B.
beganWith
Indicates that one event, process, or state started with or was initiated by another specified event, process, or state.
-
C.
startDefinedBy
chosen
Indicates that the starting point or initial state of one entity is determined, specified, or constrained by another entity.
-
D.
hasStartPattern
Indicates that something begins with, or is characterized at its outset by, a specified pattern.
-
E.
preambleBeginsWith
Indicates that the preamble of a document or text starts with a specified substring, phrase, or content.
- 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_69d7bdf366888190a8cccb982606889c |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e6a61f48190972e241e70bc392c |
completed | April 10, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69d9640ba0688190973e4e7ec8d4a8e0 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:30 p.m.