Triple
T3492442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Director of the Central Intelligence Agency |
E73765
|
entity |
| Predicate | eligibleAppointee |
P21353
|
FINISHED |
| Object | civilian |
—
|
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 | Statement: [Director of the Central Intelligence Agency, eligibleAppointee, civilian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eligibleAppointee Context triple: [Director of the Central Intelligence Agency, eligibleAppointee, civilian]
-
A.
eligibleAppointees
chosen
Indicates that certain individuals or entities meet the required criteria to be considered for a particular appointment or position.
-
B.
eligibleFrom
Indicates that a subject becomes or is considered eligible starting from a specified point in time or condition.
-
C.
positionEligible
Indicates that an entity is qualified or permitted to hold or be assigned to a particular position or role.
-
D.
eligibleWork
Indicates that a particular work satisfies the necessary conditions or criteria to qualify for a specified status, benefit, or consideration.
-
E.
eligibleWorks
Indicates that certain works meet the required criteria or conditions to qualify for a specified status, use, or consideration.
- 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_69ad85cca8d4819088494e9f3340fab5 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbabd1708190b1ca4cbc87462b5b |
completed | March 8, 2026, 6:10 p.m. |
| PD | Predicate disambiguation | batch_69adae0b34908190b2bb5766a2231f7a |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.