Triple
T8249757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minister D—— |
E192926
|
entity |
| Predicate | blackmailTarget |
P51875
|
FINISHED |
| Object | a royal lady |
—
|
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: a royal lady | Statement: [Minister D——, blackmailTarget, a royal lady]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: blackmailTarget Context triple: [Minister D——, blackmailTarget, a royal lady]
-
A.
blackmails
Indicates that one entity coerces another by threatening to reveal damaging or sensitive information unless specific demands are met.
-
B.
blackmailedFor
Indicates that one entity coerces another into doing or not doing something by threatening to reveal damaging or sensitive information about them.
-
C.
targetOfCrime
chosen
Indicates that the subject is the person, organization, or entity against whom the referenced crime is committed.
-
D.
ransom
Indicates demanding payment or concessions in exchange for releasing a person, object, or information held under threat or coercion.
-
E.
target
Indicates that one entity is the intended object, goal, or focus of another entity’s action or attention.
- 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_69ca82de7b8c81908d8106f8a53cff9b |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb78c817708190ad1c364e12083d26 |
completed | March 31, 2026, 7:33 a.m. |
| PD | Predicate disambiguation | batch_69cb36b6d5548190b665a6cce14c69f7 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:48 p.m.