Triple
T7386082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jersey coat of arms |
E170382
|
entity |
| Predicate | orientationOfLions |
P23241
|
FINISHED |
| Object | walking to the left (heraldic dexter) |
—
|
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: walking to the left (heraldic dexter) | Statement: [Jersey coat of arms, orientationOfLions, walking to the left (heraldic dexter)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orientationOfLions Context triple: [Jersey coat of arms, orientationOfLions, walking to the left (heraldic dexter)]
-
A.
lionAttitude
Indicates the nature or disposition of a lion toward another entity or situation.
-
B.
lionPosition
chosen
Indicates the spatial location or placement of a lion relative to a reference frame or environment.
-
C.
lionAttribute
Indicates that one entity has an attribute, property, or characteristic related to a lion in relation to another entity.
-
D.
lionOrigin
Indicates that one entity is the geographical or contextual origin of a lion or group of lions.
-
E.
lionArmedAndLangued
Indicates that a lion is depicted with its claws and tongue emphasized, typically by being shown and colored distinctly.
- 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_69c68a5e2c9081909e713ce866e0060a |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f1f117ec8190a97cbd0b35d5811a |
completed | March 27, 2026, 9:09 p.m. |
| PD | Predicate disambiguation | batch_69c6f0309cc88190b55d278969400294 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:08 p.m.