Triple
T37187601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wormwood |
E921358
|
entity |
| Predicate | portraysProgram |
P110358
|
FINISHED |
| Object | Project MK-Ultra |
—
|
NE NERFINISHED |
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: Project MK-Ultra | Statement: [Wormwood, portraysProgram, Project MK-Ultra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysProgram Context triple: [Wormwood, portraysProgram, Project MK-Ultra]
-
A.
programOf
Indicates that one entity is a program (such as a course of study or curriculum) that is offered, managed, or associated with another entity (such as an institution, department, or organization).
-
B.
portraysActivity
chosen
Indicates that one entity visually or narratively represents another entity engaged in a particular activity.
-
C.
narrativeProgram
Indicates that one entity functions as a narrative or storyline framework within which another entity’s actions, events, or roles are organized or structured.
-
D.
viewOnPrograms
Indicates the stance, opinion, or perspective that an entity holds regarding certain programs (such as policies, initiatives, or media content).
-
E.
famousProgram
Indicates that a program is widely recognized or well-known, typically for its impact, quality, or popularity.
- 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_69f76ea250bc819083f28d81de25cd0c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ff965f9be48190b015b788207be676 |
completed | May 9, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69ff95d3015c8190b9d293fe31b859c3 |
completed | May 9, 2026, 8:15 p.m. |
Created at: May 3, 2026, 4:15 p.m.