Triple
T12821706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Major Defense Acquisition Program |
E306544
|
entity |
| Predicate | requiresDecision |
P106530
|
FINISHED |
| Object | Milestone A approval |
—
|
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: Milestone A approval | Statement: [Major Defense Acquisition Program, requiresDecision, Milestone A approval]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresDecision Context triple: [Major Defense Acquisition Program, requiresDecision, Milestone A approval]
-
A.
includesDecisionOn
Indicates that one item or process contains, encompasses, or explicitly addresses a particular decision or determination.
-
B.
decisionsAre
Indicates that certain choices, judgments, or resolutions possess a specified quality, status, or classification.
-
C.
decisionType
Indicates the specific category or nature of a decision associated with an entity or event.
-
D.
decisionsSubjectTo
Indicates that certain decisions are constrained by, dependent on, or must comply with specified conditions, approvals, or oversight.
-
E.
requiresAdviceAndApprovalOf
Indicates that one entity can proceed with an action or decision only if it first seeks guidance and obtains formal approval from another entity.
- F. None of above. chosen
Provenance (4 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_69d7bdf46c448190b1faa55aaacb6317 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e9fcc8c8190a926ab0481d28f14 |
completed | April 10, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69d964100f7481909a197396003d4a71 |
completed | April 10, 2026, 8:56 p.m. |
| PDg | Predicate description generation | batch_69d96d88be0481908c311f1e71b61e70 |
completed | April 10, 2026, 9:37 p.m. |
Created at: April 9, 2026, 5:32 p.m.