Triple
T38428426
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Kettle |
E903727
|
entity |
| Predicate | soughtPeaceWith |
P34253
|
FINISHED |
| Object | United States government |
—
|
NE NERFINISHED |
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: United States government | Statement: [Black Kettle, soughtPeaceWith, United States government]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: soughtPeaceWith Context triple: [Black Kettle, soughtPeaceWith, United States government]
-
A.
attemptedArmisticeWith
chosen
Indicates an effort by one party to initiate or negotiate a ceasefire or peace agreement with another party.
-
B.
maintainedPeaceWith
Indicates that two entities sustained a state of peace or non-conflict with each other over a period of time.
-
C.
peaceTerms
Indicates the conditions or agreements proposed or accepted by parties to establish or maintain peace after or during a conflict.
-
D.
hasPeaceAccord
Indicates that a formal peace agreement or treaty exists between the related entities, establishing terms to end or prevent conflict.
-
E.
peaceConcludedUnder
Indicates that a peace agreement or treaty was formally established under specified conditions, authority, or circumstances.
- 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_69f76e6a2024819081aa04f4932f89d2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.