Triple
T7112802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Office of Special Counsel |
E165744
|
entity |
| Predicate | protectsFromRetaliationFor |
P13930
|
FINISHED |
| Object | disclosures of violations of law |
—
|
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: disclosures of violations of law | Statement: [United States Office of Special Counsel, protectsFromRetaliationFor, disclosures of violations of law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protectsFromRetaliationFor Context triple: [United States Office of Special Counsel, protectsFromRetaliationFor, disclosures of violations of law]
-
A.
protectedBy
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
B.
protects
Indicates taking action to keep someone or something safe from harm, danger, or negative effects.
-
C.
providesProtectionAgainst
Indicates that one entity serves to guard, shield, or defend another entity from a specified harm, threat, or adverse effect.
-
D.
aimsToProtect
Indicates an intention or purpose to safeguard or defend one entity, value, or condition from harm, risk, or undesirable outcomes.
-
E.
protectsRight
chosen
Indicates that one entity safeguards, upholds, or defends the legal or moral rights of another entity.
- 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_69c6888120f081908f8f01b201dc4a4c |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e5ef813c8190bec0ab0cbae430e5 |
completed | March 27, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69c6e1c4f9788190830288d00cc37026 |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:43 p.m.