Triple
T18512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Director of National Intelligence |
E365
|
entity |
| Predicate | officeEstablished |
P1383
|
FINISHED |
| Object | April 21, 2005 |
—
|
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: April 21, 2005 | Statement: [Director of National Intelligence, officeEstablished, April 21, 2005]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeEstablished Context triple: [Director of National Intelligence, officeEstablished, April 21, 2005]
-
A.
residentCompany
Indicates that a company is based in, operates from, or has its primary residence in a particular location or jurisdiction.
-
B.
officeStart
chosen
Indicates the time or date at which an entity’s term, role, or period of holding office begins.
-
C.
foundedAfter
Indicates that one entity was founded at a later time than another entity.
-
D.
foundedOn
Indicates that an entity was established, created, or brought into existence on a specific date or point in time.
-
E.
establishes
Indicates that one entity initiates, creates, or formally sets up another entity, relationship, or state, often giving it official or recognized status.
- 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_69a240778d288190815c0052ebbbcc91 |
completed | Feb. 28, 2026, 1:10 a.m. |
| NER | Named-entity recognition | batch_69a246cbca108190a92478df126d9bf8 |
completed | Feb. 28, 2026, 1:37 a.m. |
| PD | Predicate disambiguation | batch_69a2464f61648190ac690044be194972 |
completed | Feb. 28, 2026, 1:35 a.m. |
Created at: Feb. 28, 2026, 1:14 a.m.