Triple
T19721754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty 4 |
E473625
|
entity |
| Predicate | landCession |
P76587
|
FINISHED |
| Object | large portions of southern prairie lands |
—
|
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: large portions of southern prairie lands | Statement: [Treaty 4, landCession, large portions of southern prairie lands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: landCession Context triple: [Treaty 4, landCession, large portions of southern prairie lands]
-
A.
requiredTerritorialCessionBy
Indicates that one party is obligated to transfer control or ownership of territory to another party.
-
B.
earlierCessionInTreaty
Indicates that one party transferred or ceded something to another at an earlier point within the sequence of cessions specified in a treaty.
-
C.
wasCededAfter
Indicates that control or ownership of one entity was formally transferred to another entity following a specified event or point in time.
-
D.
territoryAcquired
chosen
Indicates that one entity has gained control, ownership, or possession of a geographic area from another entity.
-
E.
countryReceivingSovereignty
Indicates the country that gains or is granted sovereign authority or control in a given context or agreement.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e649f587d88190bf519fec7ce634d3 |
completed | April 20, 2026, 3:44 p.m. |
| PD | Predicate disambiguation | batch_69e5304a7aac8190ac13f75f0c008e45 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:46 p.m.