Triple
T26493080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Investment Committee (CalPERS) |
E669208
|
entity |
| Predicate | typeOfDecisionMaking |
P2165
|
FINISHED |
| Object | policy-level investment decisions |
—
|
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: policy-level investment decisions | Statement: [Investment Committee (CalPERS), typeOfDecisionMaking, policy-level investment decisions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfDecisionMaking Context triple: [Investment Committee (CalPERS), typeOfDecisionMaking, policy-level investment decisions]
-
A.
decisionMaking
Indicates the process by which an entity evaluates options and selects a course of action among alternatives.
-
B.
decisionMakerType
Indicates the role or category of entity responsible for making a particular decision.
-
C.
decisionType
chosen
Indicates the specific category or nature of a decision associated with an entity or event.
-
D.
decisionMakingRole
Indicates that an entity holds responsibility or authority in making decisions for or on behalf of another entity or group.
-
E.
decisionMakingModel
Indicates a relationship where an entity uses or is associated with a specific model or framework for making decisions.
- 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_69eeb319007081909642b414b114b35a |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
Created at: April 27, 2026, 1:06 a.m.