Triple
T13782617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | McCarran–Walter Act |
E331166
|
entity |
| Predicate | TrumanDescribedAs |
P100537
|
FINISHED |
| Object | un-American |
—
|
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: un-American | Statement: [McCarran–Walter Act, TrumanDescribedAs, un-American]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: TrumanDescribedAs Context triple: [McCarran–Walter Act, TrumanDescribedAs, un-American]
-
A.
TrumanCharacterization
chosen
Indicates how the character of Truman is portrayed or described in terms of traits, behavior, or role.
-
B.
TrumanParty
Indicates the political party affiliation associated with Harry S. Truman.
-
C.
portraysUSPresident
Indicates that one entity depicts, represents, or plays the role of a U.S. President in some medium or context.
-
D.
associatedPresident
Indicates a relationship where a person, organization, event, or entity is linked or connected to a specific president in a relevant or significant way.
-
E.
otherMajorPresidency
Indicates that the subject held a significant presidential position in a context other than their primary or most notable presidency.
- 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_69d81c58feb08190a77bca8bf7d6d20f |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de0247ccc881908dad7b547221f15d |
completed | April 14, 2026, 9 a.m. |
| PD | Predicate disambiguation | batch_69dbc85fb600819098a2aab48169be96 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:11 p.m.