Triple
T12449758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Dragon |
E297498
|
entity |
| Predicate | orientationOnFlag |
P41721
|
FINISHED |
| Object | passant |
—
|
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: passant | Statement: [Red Dragon, orientationOnFlag, passant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orientationOnFlag Context triple: [Red Dragon, orientationOnFlag, passant]
-
A.
orientationInFlag
chosen
Indicates the spatial orientation or alignment of an entity as it appears within a flag.
-
B.
orientationInducedBy
Indicates that the orientation of one entity is determined or caused by the orientation or configuration of another entity.
-
C.
orientationType
Indicates the specific kind or category of orientation relationship that exists between entities (such as spatial, directional, or alignment-based orientation).
-
D.
orientation
Indicates the relative directional alignment or facing of one entity with respect to another or to a reference frame.
-
E.
orientationPrinciple
Indicates the guiding rule or standard that directs how something is positioned, aligned, or oriented in relation to other things.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95151e7348190a1d4953a8b416a13 |
completed | April 10, 2026, 7:36 p.m. |
| PD | Predicate disambiguation | batch_69d94d3c27a08190a0237200203e476d |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:56 p.m.