Triple
T30844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sather Gate |
E614
|
entity |
| Predicate | imageDepicts |
P1581
|
FINISHED |
| Object | University of California, Berkeley campus entrance |
—
|
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: University of California, Berkeley campus entrance | Statement: [Sather Gate, imageDepicts, University of California, Berkeley campus entrance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: imageDepicts Context triple: [Sather Gate, imageDepicts, University of California, Berkeley campus entrance]
-
A.
depictsPerson
Indicates that one entity visually represents or portrays a specific person.
-
B.
depicts
chosen
Indicates that one entity visually represents, portrays, or shows another entity.
-
C.
isAbout
Indicates that one entity has as its subject, focus, or primary concern the content, topic, or theme represented by another entity.
-
D.
describes
Indicates that one entity provides an explanation, representation, or account of another entity or concept.
-
E.
signatureImage
Indicates that an entity has an associated image that visually represents its signature.
- 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a2490d80a0819083bf604c1229e903 |
completed | Feb. 28, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69a2486eb01881909241540dda28e1ff |
completed | Feb. 28, 2026, 1:44 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.