Triple
T19133577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gates of Hades |
E468376
|
entity |
| Predicate | originalNameRefersTo |
P104716
|
FINISHED |
| Object | Haidou pylai (gates of Hades) |
—
|
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: Haidou pylai (gates of Hades) | Statement: [Gates of Hades, originalNameRefersTo, Haidou pylai (gates of Hades)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalNameRefersTo Context triple: [Gates of Hades, originalNameRefersTo, Haidou pylai (gates of Hades)]
-
A.
hasOriginalNameOf
chosen
Indicates that one entity is the original or earlier name from which another entity’s current or later name is derived.
-
B.
originalNameLanguage
Indicates that the specified language is the language in which an entity’s original or primary name was expressed.
-
C.
memberOriginalName
Indicates that the relationship specifies the original or former name of a member entity before any renaming or changes.
-
D.
refersToOfficialName
Indicates that one entity is referencing or using the formally recognized, official name of another entity.
-
E.
canonicallyReferredToAs
Indicates that one entity is the officially recognized or standard name or label by which another entity is known.
- 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_69d8dd0796a48190b34ce4cd9d3f3be5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3eb325081909035beefd1c9daf0 |
completed | April 20, 2026, 8:29 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b085288190b974d649e12e0844 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:05 p.m.