Triple
T32329169
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Pharaoh's Daughter |
E825999
|
entity |
| Predicate | originalRoleCreated |
P118249
|
FINISHED |
| Object | Aspicia |
—
|
NE NERFINISHED |
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: Aspicia | Statement: [The Pharaoh's Daughter, originalRoleCreated, Aspicia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalRoleCreated Context triple: [The Pharaoh's Daughter, originalRoleCreated, Aspicia]
-
A.
firstCreatorRole
Indicates the specific role or capacity in which the primary or earliest creator of an entity contributed to its creation.
-
B.
roleCreatedFor
Indicates that a particular role was established or defined specifically for a given entity or purpose.
-
C.
originalServiceRole
Indicates that an entity holds or is associated with the initial or primary service-related role in a given context or system.
-
D.
createdByCharacterRole
Indicates that something (such as a work, item, or event) was brought into existence or produced by an entity acting in a specific character role.
-
E.
roleInOrigin
chosen
Indicates that an entity holds or held a specific role, function, or position within the context of its origin or source.
- 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_69f34912d0c48190bba75770660320e9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a019579463c8190b51e39183b57bbaf |
completed | May 11, 2026, 8:38 a.m. |
| PD | Predicate disambiguation | batch_6a0192d309488190a3d86c93e7138c77 |
completed | May 11, 2026, 8:26 a.m. |
Created at: May 1, 2026, 12:47 a.m.