Triple
T16348064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Butte du Lion de Waterloo |
E396985
|
entity |
| Predicate | lionMaterial |
P1272
|
FINISHED |
| Object | cast iron |
—
|
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: cast iron | Statement: [Butte du Lion de Waterloo, lionMaterial, cast iron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lionMaterial Context triple: [Butte du Lion de Waterloo, lionMaterial, cast iron]
-
A.
lionAttribute
Indicates that one entity has an attribute, property, or characteristic related to a lion in relation to another entity.
-
B.
lionArmedAndLangued
Indicates that a lion is depicted with its claws and tongue emphasized, typically by being shown and colored distinctly.
-
C.
lionCrowned
Indicates that an entity (typically a lion) is depicted or described as wearing a crown, symbolizing rulership, authority, or elevated status.
-
D.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
E.
lionTincture
Indicates a heraldic relationship where a lion is depicted in a specific color or pattern (tincture) on a coat of arms or shield.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2da1038d88190b8292cfe71bc4f2a |
completed | April 18, 2026, 1:10 a.m. |
| PD | Predicate disambiguation | batch_69e226f37ecc819082af58b29b4e39d1 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:07 a.m.