Triple
T66210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr. Secretary |
E1319
|
entity |
| Predicate | addressedTo |
P265
|
FINISHED |
| Object | civilian head of the Department of Defense |
—
|
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: civilian head of the Department of Defense | Statement: [Mr. Secretary, addressedTo, civilian head of the Department of Defense]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addressedTo Context triple: [Mr. Secretary, addressedTo, civilian head of the Department of Defense]
-
A.
givenTo
Indicates that something is transferred or presented by one entity to another as a recipient.
-
B.
address
Indicates that one entity directs spoken or written communication specifically to another entity.
-
C.
governmentBodyAddressed
Indicates that a particular government body is the one being directly addressed or targeted by a communication, action, or request.
-
D.
addresses
chosen
Indicates that one entity directs speech, communication, or written correspondence specifically toward another entity.
-
E.
notableRecipient
Indicates that an entity has received a notable award, honor, or recognition from 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_69a24ba4f760819081f6638a3c70538a |
completed | Feb. 28, 2026, 1:57 a.m. |
| NER | Named-entity recognition | batch_69a2516eda54819090f5c14384d4eab1 |
completed | Feb. 28, 2026, 2:22 a.m. |
| PD | Predicate disambiguation | batch_69a24ea5c140819080409a968c8d2ce8 |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:02 a.m.