Triple
T13841054
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fernandel |
E332655
|
entity |
| Predicate | eyeCatchingFeature |
P37670
|
FINISHED |
| Object | highly expressive face |
—
|
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: highly expressive face | Statement: [Fernandel, eyeCatchingFeature, highly expressive face]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eyeCatchingFeature Context triple: [Fernandel, eyeCatchingFeature, highly expressive face]
-
A.
focusFeature
Indicates that one entity is the primary or emphasized feature, aspect, or attribute being highlighted or concentrated on in relation to another.
-
B.
eyeCharacteristic
Indicates a relationship where an entity possesses a specific attribute, feature, or quality of its eyes.
-
C.
notableFeatureOn
Indicates that one entity is a prominent or distinguishing feature located on or part of another entity.
-
D.
keyFeature
Indicates that something is a primary, distinguishing, or most important feature of an entity.
-
E.
iconicFeature
chosen
Indicates that something serves as a distinctive, widely recognized characteristic or symbol of another entity.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02ae5e4c8190ad85ad2968bc71b2 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.