Triple
T35709425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Un bon bock |
E1031810
|
entity |
| Predicate | hasSurvivingElements |
P89335
|
FINISHED |
| Object | still images and written descriptions only |
—
|
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: still images and written descriptions only | Statement: [Un bon bock, hasSurvivingElements, still images and written descriptions only]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSurvivingElements Context triple: [Un bon bock, hasSurvivingElements, still images and written descriptions only]
-
A.
hasSurvivingElement
chosen
Indicates that an entity retains at least one remaining or extant part, instance, or component that still exists.
-
B.
hasSurvivalElements
Indicates that something includes features or conditions related to survival, such as resource management, threat avoidance, or sustaining life over time.
-
C.
hasSurvivors
Indicates that one or more entities continue to exist or remain alive after a particular event, condition, or incident.
-
D.
hasSurvivingText
Indicates that there exists at least one extant or preserved textual record associated with the subject.
-
E.
hasLivingComponents
Indicates that an entity includes or is composed of one or more living or biological components.
- 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_69f76e0df1d08190965b1c6dff94c391 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fff09dae088190bd8460060d778feb |
completed | May 10, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_69fff0027c5c8190baa5c7a15852cbe0 |
completed | May 10, 2026, 2:40 a.m. |
Created at: May 3, 2026, 4:05 p.m.