Triple
T3413881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SPLASH |
E71961
|
entity |
| Predicate | hasComponentEvent |
P6285
|
FINISHED |
| Object | workshops |
—
|
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: workshops | Statement: [SPLASH, hasComponentEvent, workshops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasComponentEvent Context triple: [SPLASH, hasComponentEvent, workshops]
-
A.
hasComponentCurrent
Indicates that an entity currently includes or contains a specific component as part of its present composition or structure.
-
B.
hasComponentModel
Indicates that an entity includes or is associated with a specific component model as part of its structure or configuration.
-
C.
hasEventType
Indicates that an event is associated with, or classified under, a specific type or category of event.
-
D.
hasSubEvent
chosen
Indicates that an event is composed of, or includes as part of its structure, another event that occurs within it.
-
E.
hasComponentCommand
Indicates that an entity includes or controls another entity as a subordinate or component command within an organizational or command structure.
- 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_69ad85ac312481909e7027ced1456a9f |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb927e8d081908a5ab283da93beb2 |
completed | March 8, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69adadfcbc38819080852c18240451c5 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:15 p.m.