Triple
T31865353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Head-Smashed-In Buffalo Jump |
E813434
|
entity |
| Predicate | latestIntensiveUseApprox |
P161221
|
FINISHED |
| Object | 19th century |
—
|
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: 19th century | Statement: [Head-Smashed-In Buffalo Jump, latestIntensiveUseApprox, 19th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: latestIntensiveUseApprox Context triple: [Head-Smashed-In Buffalo Jump, latestIntensiveUseApprox, 19th century]
-
A.
intensiveUse
Indicates a relationship where an entity is used in a concentrated, frequent, or high-intensity manner by another entity.
-
B.
latestInterval
Indicates that the related interval is the most recent or last occurring time span among a set of intervals.
-
C.
maximumUsage
Indicates the highest allowable or observed amount, frequency, or extent to which something can be used within a defined context or period.
-
D.
latestMajorUseDate
chosen
Indicates the most recent calendar date on which the entity was used in a significant or primary way.
-
E.
latestCommonUse
Indicates the most recent point in time at which two or more entities were used or applicable in common.
- 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_69f348ecb07481909c8f72619131b115 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b07340088190a0cd5b1ebecc5424 |
completed | May 3, 2026, 2:18 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:53 p.m.