Triple
T751068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Weeping Angels |
E15447
|
entity |
| Predicate | materialStateWhenUnobserved |
P19082
|
FINISHED |
| Object | Unknown non-stone form |
—
|
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: Unknown non-stone form | Statement: [Weeping Angels, materialStateWhenUnobserved, Unknown non-stone form]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: materialStateWhenUnobserved Context triple: [Weeping Angels, materialStateWhenUnobserved, Unknown non-stone form]
-
A.
notObservedIn
Indicates that a particular entity, event, or property has not been detected, recorded, or seen within a specified context, dataset, or environment.
-
B.
observerStatusIn
Indicates that an entity’s status or role is defined or valid within a specified observational context, system, or environment.
-
C.
associatedState
Indicates that one entity is linked or connected to a particular state, condition, or status of another entity.
-
D.
visibleAt
Indicates that one entity can be seen or perceived from a specific location, viewpoint, or context at a given time.
-
E.
sourceState
Indicates the original or starting state from which a transition, change, or process begins.
- 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_69a493599a0081908da65f3407af1ef2 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a64c67748190aef3522b4b428563 |
completed | March 1, 2026, 8:49 p.m. |
| PD | Predicate disambiguation | batch_69a4a501c4cc81908de6d63e3d4f60d7 |
completed | March 1, 2026, 8:43 p.m. |
| PDg | Predicate description generation | batch_69a4a5bed20c81909ecc28bf42594e72 |
completed | March 1, 2026, 8:46 p.m. |
Created at: March 1, 2026, 7:37 p.m.