Triple
T4561916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hospitality of King Keleos |
E121810
|
entity |
| Predicate | timeWithinMyth |
P20414
|
FINISHED |
| Object | period of Demeter’s mourning for Persephone |
—
|
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: period of Demeter’s mourning for Persephone | Statement: [Hospitality of King Keleos, timeWithinMyth, period of Demeter’s mourning for Persephone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeWithinMyth Context triple: [Hospitality of King Keleos, timeWithinMyth, period of Demeter’s mourning for Persephone]
-
A.
timeInMyth
chosen
Indicates that an entity exists or occurs during a specific time period within a mythological narrative or tradition.
-
B.
timeExistence
Indicates the period or duration during which an entity exists or is valid.
-
C.
time
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
D.
timePeriod
Indicates the specific span or interval of time during which an event, state, or relationship occurs or is valid.
-
E.
timePeriodWithin
Indicates that one time period is entirely contained within the bounds of another time period.
- 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_69bd463f156881908a99aca69c5721ac |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd582f21648190b49284eb61b618c9 |
completed | March 20, 2026, 2:22 p.m. |
| PD | Predicate disambiguation | batch_69bd52254c648190a5144cfe8fa7e409 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:09 p.m.