Triple
T11642943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Executive Order 11375 |
E276703
|
entity |
| Predicate | previousProtectionsIncluded |
P52471
|
FINISHED |
| Object | race |
—
|
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: race | Statement: [Executive Order 11375, previousProtectionsIncluded, race]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousProtectionsIncluded Context triple: [Executive Order 11375, previousProtectionsIncluded, race]
-
A.
previousProtectionStatus
Indicates the protection or security state an entity was in before its current protection status.
-
B.
previousVersionIncluded
Indicates that an earlier version of an entity was contained within, or formed part of, the current entity.
-
C.
formerlyIncluded
chosen
Indicates that an entity was previously part of, contained in, or a member of another entity, but is no longer included.
-
D.
previouslyCovered
Indicates that the subject has already been addressed, discussed, or dealt with at an earlier time or in a prior context.
-
E.
protectionPolicy
Indicates that one entity establishes or enforces rules or measures to safeguard another entity from harm, loss, or risk.
- 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_69d6aafbb3c081908a9cdb4ecb8d981d |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a2cb4ca88190a9322f08416d3974 |
completed | April 10, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69d85dd94bdc819091fa2ed33eb31624 |
completed | April 10, 2026, 2:18 a.m. |
Created at: April 8, 2026, 9:39 p.m.