Triple
T36360356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady Birth-giver |
E895471
|
entity |
| Predicate | typeOfGoddessTitle |
P128304
|
FINISHED |
| Object | mother goddess epithet |
—
|
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: mother goddess epithet | Statement: [Lady Birth-giver, typeOfGoddessTitle, mother goddess epithet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfGoddessTitle Context triple: [Lady Birth-giver, typeOfGoddessTitle, mother goddess epithet]
-
A.
devotionalTitleType
chosen
Indicates the specific kind or category of title used in a devotional context (such as a form of address or honorific used in religious devotion).
-
B.
templeTitleOf
Indicates that one entity is the formal religious or ceremonial title held by another entity within a temple or sacred context.
-
C.
cultTitleOfPersephone
Indicates that the subject holds a cultic or religious title specifically associated with the deity Persephone.
-
D.
ritualTitle
Indicates the formal name or designation assigned to a specific ritual within a cultural, religious, or ceremonial context.
-
E.
titleOfTitle
Indicates that one title is the title of another title (e.g., a sub-title or alternate title associated with a primary title).
- 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_69f76e5044248190b390d8887dc03254 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a03008316dc8190a9f6faf48d25a4f8 |
completed | May 12, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_6a030023e66881909ea79f1365ab538a |
completed | May 12, 2026, 10:25 a.m. |
Created at: May 3, 2026, 4:09 p.m.