Triple
T10479651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DDT |
E247136
|
entity |
| Predicate | yearBannedInUnitedStates |
P43036
|
FINISHED |
| Object | 1972 |
—
|
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: 1972 | Statement: [DDT, yearBannedInUnitedStates, 1972]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearBannedInUnitedStates Context triple: [DDT, yearBannedInUnitedStates, 1972]
-
A.
bannedInCountry
chosen
Indicates that something is officially prohibited or not allowed within the jurisdiction of a specified country.
-
B.
suppressedInCountry
Indicates that an entity (such as content, activity, or information) is restricted, censored, or otherwise prevented from being available or expressed within a specified country.
-
C.
legalStatusInManyCountries
Indicates that the subject has a particular legal classification or standing that is recognized across numerous countries.
-
D.
politicalRestriction
Indicates that there are limitations or prohibitions imposed on an entity’s political activities, rights, or participation.
-
E.
legalizedIn
Indicates that an action, substance, or practice is permitted by law within a specified jurisdiction or region.
- 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_69d381c16c248190a2fe5b471e584e9c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5095b2ec881909e1220d83e750a75 |
completed | April 7, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_69d4fb84bafc8190819757b93620508a |
completed | April 7, 2026, 12:41 p.m. |
Created at: April 6, 2026, 12:22 p.m.