Triple
T2170932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luiseño people |
E48421
|
entity |
| Predicate | currentActivities |
P8834
|
FINISHED |
| Object | language revitalization |
—
|
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: language revitalization | Statement: [Luiseño people, currentActivities, language revitalization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentActivities Context triple: [Luiseño people, currentActivities, language revitalization]
-
A.
activityTime
Indicates the time period during which an activity occurs or is scheduled to take place.
-
B.
currentActivityLevel
Indicates the present intensity or degree of activity that an entity is engaged in at a given moment.
-
C.
activityStartApprox
Indicates that the start time of an activity is known only approximately, rather than as an exact timestamp.
-
D.
activityType
chosen
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
E.
typicalActivity
Indicates that an entity is commonly or characteristically engaged in a particular activity.
- 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_69a88aa3faa48190995b233af6525815 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc1559ff481908efe3f214b2570dc |
completed | March 7, 2026, 6:10 a.m. |
| PD | Predicate disambiguation | batch_69abbd9efc1c81909a65044a1ffc9038 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:45 p.m.