Triple
T155816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord Kitchener Wants You poster |
E3178
|
entity |
| Predicate | hasVisualFeature |
P182
|
FINISHED |
| Object | direct gaze at viewer |
—
|
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: direct gaze at viewer | Statement: [Lord Kitchener Wants You poster, hasVisualFeature, direct gaze at viewer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVisualFeature Context triple: [Lord Kitchener Wants You poster, hasVisualFeature, direct gaze at viewer]
-
A.
hasNotableFeature
Indicates that an entity possesses a specific characteristic, trait, or attribute that is considered significant or noteworthy.
-
B.
hasFeature
chosen
Indicates that an entity possesses, exhibits, or includes a particular characteristic, attribute, or component.
-
C.
hasPerception
Indicates that one entity is aware of, senses, or recognizes another entity or phenomenon.
-
D.
hasCulturalFeature
Indicates that an entity possesses, includes, or is characterized by a particular cultural element, attribute, or landmark.
-
E.
vision
Indicates that an entity perceives another entity or object visually, using sight.
- 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_69a2527757ec819090b8becb2cf1a862 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a258808ff08190a06b6206f635612b |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a2565ded588190a27319aaa0130b4f |
completed | Feb. 28, 2026, 2:43 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.