Triple
T36804840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arms of Montfort-l’Amaury |
E909418
|
entity |
| Predicate | languedTincture |
P203302
|
FINISHED |
| Object | azure |
—
|
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: azure | Statement: [Arms of Montfort-l’Amaury, languedTincture, azure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languedTincture Context triple: [Arms of Montfort-l’Amaury, languedTincture, azure]
-
A.
tongueTincture
Indicates that an entity applies or administers a tincture by placing it on or under the tongue.
-
B.
tinctureOfTongueAndClaws
Indicates a condition or effect in which both speech (tongue) and physical attacks (claws) are imbued with a special, often magical or poisonous, potency.
-
C.
fieldTincture
Indicates the heraldic tincture (color, metal, or fur) applied to the main background field of a coat of arms.
-
D.
tinctureOfKey
Indicates that one entity is a tincture (medicinal or alcoholic extract) derived from, containing, or primarily based on another entity designated as the key ingredient.
-
E.
tinctureOfPale
Indicates that one entity is a tincture (medicinal or alcoholic extract) derived from or characterized by the pale aspect, quality, or component 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_69f76e7cbbf48190891227b14d041139 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a014f7602988190b8f86cb431a9cf12 |
completed | May 11, 2026, 3:39 a.m. |
| PD | Predicate disambiguation | batch_6a014a70ea748190bd86fb9f218103ba |
completed | May 11, 2026, 3:18 a.m. |
| PDg | Predicate description generation | batch_6a014f751520819088cf1e697e0668ff |
completed | May 11, 2026, 3:39 a.m. |
Created at: May 3, 2026, 4:12 p.m.