Triple
T36659968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen Elizabeth |
E905092
|
entity |
| Predicate | childrenFateThreatenedBy |
P956
|
FINISHED |
| Object | Richard, Duke of Gloucester |
—
|
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: Richard, Duke of Gloucester | Statement: [Queen Elizabeth, childrenFateThreatenedBy, Richard, Duke of Gloucester]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: childrenFateThreatenedBy Context triple: [Queen Elizabeth, childrenFateThreatenedBy, Richard, Duke of Gloucester]
-
A.
fateOfChild
Indicates the outcome or destiny that ultimately befalls a child as a result of certain circumstances, actions, or events.
-
B.
numberOfChildVictims
Indicates the count of individuals who are victims and are classified as children in the context of the described event or situation.
-
C.
childrenKilledBy
Indicates that the children of a given entity were killed by another specified entity or agent.
-
D.
threatenedBy
chosen
Indicates that one entity poses a danger or potential harm to another entity.
-
E.
threatsFaced
Indicates that an entity is exposed to or experiences specific dangers, risks, or harmful conditions.
- 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_69f76e6e3b908190970251b30f76ad71 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f9fd6834cc8190aa27153d6a99f3bb |
completed | May 5, 2026, 2:23 p.m. |
| PD | Predicate disambiguation | batch_69f7cf769338819092a5f42653dcc956 |
completed | May 3, 2026, 10:43 p.m. |
Created at: May 3, 2026, 4:11 p.m.