Triple
T14944726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perseus and Andromeda |
E372626
|
entity |
| Predicate | depictsCreatureType |
P49328
|
FINISHED |
| Object | marine monster |
—
|
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: marine monster | Statement: [Perseus and Andromeda, depictsCreatureType, marine monster]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsCreatureType Context triple: [Perseus and Andromeda, depictsCreatureType, marine monster]
-
A.
depictsCharacterType
chosen
Indicates that one entity visually represents or portrays a character of a specified type or role.
-
B.
depictionType
Indicates the specific manner or style in which something is visually represented or depicted.
-
C.
mentionsCreature
Indicates that one entity refers to or brings up a particular creature in some form of communication or content.
-
D.
usesCreature
Indicates that one entity employs, controls, or relies on a creature to perform an action or fulfill a function.
-
E.
typicallyDepicts
Indicates that one entity is most commonly or characteristically portrayed or represented by the other in depictions or images.
- 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_69d85cc9da0c81908d583ca3f63a3908 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded68d20048190a403af85fe43dede |
completed | April 15, 2026, 12:06 a.m. |
| PD | Predicate disambiguation | batch_69de9a588c2c8190b1245a1c406f447c |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:39 a.m.