Triple
T26076450
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wrath of Artemis |
E657697
|
entity |
| Predicate | depictsAspectOfArtemis |
P86688
|
FINISHED |
| Object | vengeful aspect |
—
|
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: vengeful aspect | Statement: [Wrath of Artemis, depictsAspectOfArtemis, vengeful aspect]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depictsAspectOfArtemis Context triple: [Wrath of Artemis, depictsAspectOfArtemis, vengeful aspect]
-
A.
ArtemisIs
Indicates that something or someone is identified as, or has the status/role of, Artemis.
-
B.
ArtemisISplashdownDate
Indicates the calendar date on which the Artemis I mission completed splashdown back on Earth.
-
C.
portraysApolloAs
Indicates that one entity represents or depicts Apollo in a particular way or role.
-
D.
associatedGoddess
Indicates that one entity is recognized as the goddess traditionally linked or connected to another entity (such as a place, concept, or deity).
-
E.
depictedDeity
chosen
Indicates that one entity is a deity who is shown or represented in an image, artwork, or visual depiction associated with 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_69ee5bbe539081909efc7f9dd7c1b53c |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f650c70d7c819093d9a0f005f7c8d5 |
completed | May 2, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69f64cab1f648190a2a9460690d18a37 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 26, 2026, 7:34 p.m.