Triple
T651504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Havdalah ceremony |
E11353
|
entity |
| Predicate | timeRequirement |
P1936
|
FINISHED |
| Object | after appearance of three stars on Saturday night |
—
|
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: after appearance of three stars on Saturday night | Statement: [Havdalah ceremony, timeRequirement, after appearance of three stars on Saturday night]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeRequirement Context triple: [Havdalah ceremony, timeRequirement, after appearance of three stars on Saturday night]
-
A.
workLengthRequirement
Indicates that there is a specified minimum or exact duration of work required for something (e.g., a job, task, or role).
-
B.
frequencyRequirement
Indicates a constraint specifying how often an action, event, or condition must occur within a given context or time frame.
-
C.
time
chosen
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
D.
timePeriod
Indicates the specific span or interval of time during which an event, state, or relationship occurs or is valid.
-
E.
timeType
Indicates the specific temporal category or classification associated with a time-related entity or value (e.g., duration, point in time, interval, or recurrence type).
- 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_69a493266a2881909daf4c40f719dee8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49f35acb08190a3a8248023ce07f9 |
completed | March 1, 2026, 8:19 p.m. |
| PD | Predicate disambiguation | batch_69a49d1001088190aa7ca3c8f2ad0e32 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:36 p.m.