Triple
T11860064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Knight's Tale |
E282135
|
entity |
| Predicate | positionInFrame |
P101899
|
FINISHED |
| Object | first tale in The Canterbury Tales sequence |
—
|
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: first tale in The Canterbury Tales sequence | Statement: [The Knight's Tale, positionInFrame, first tale in The Canterbury Tales sequence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionInFrame Context triple: [The Knight's Tale, positionInFrame, first tale in The Canterbury Tales sequence]
-
A.
positionInField
Indicates the specific role, location, or functional placement an entity occupies within a defined field, domain, or area of activity.
-
B.
positionInPage
Indicates the specific location or placement of an element within a page’s layout or structure.
-
C.
positionInMovement
Indicates the specific role or placement an entity holds within a broader movement or collective action.
-
D.
positionInEvent
Indicates the specific role, placement, or ordering that an entity has within a particular event.
-
E.
positionInState
Indicates that one entity occupies or holds a specific position, role, or status within a particular state or condition of 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a69a099c8190a674db64c50eca5a |
completed | April 10, 2026, 7:28 a.m. |
| PD | Predicate disambiguation | batch_69d8a2573dbc8190ab432e8e28fde6cc |
completed | April 10, 2026, 7:10 a.m. |
| PDg | Predicate description generation | batch_69d8a43cc0c881909fed7cd759fe90b1 |
completed | April 10, 2026, 7:18 a.m. |
Created at: April 8, 2026, 9:43 p.m.