Triple
T1064979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mardi Gras celebrations |
E22989
|
entity |
| Predicate | marksOccasion |
P23026
|
FINISHED |
| Object | last day before Lent |
—
|
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: last day before Lent | Statement: [Mardi Gras celebrations, marksOccasion, last day before Lent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marksOccasion Context triple: [Mardi Gras celebrations, marksOccasion, last day before Lent]
-
A.
displayOccasion
Indicates the event, context, or situation during which something is presented, shown, or made visible.
-
B.
servingOccasion
Indicates the occasion, event, or context during which something (typically food or drink) is served.
-
C.
primaryOccasion
Indicates that one occasion is the main or most significant event associated with a given context, entity, or activity.
-
D.
announcementOccasion
Indicates the specific event, context, or circumstance on the basis of which an announcement is made.
-
E.
holidayAssociation
Indicates a relationship where one entity is connected to, themed around, or designated for a particular holiday.
- F. None of above. chosen
Provenance (4 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_69a493dada0481909c43649f9843ea91 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b90f91248190ace1534a51b82bdd |
completed | March 1, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69a4b7359eb881909c868a558861cc18 |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b7da38888190a118ef20ce4ae9aa |
completed | March 1, 2026, 10:04 p.m. |
Created at: March 1, 2026, 7:42 p.m.