Triple
T1177002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penelope |
E25049
|
entity |
| Predicate | durationOfOdysseusAbsence |
P20414
|
FINISHED |
| Object | about twenty years in the myth |
—
|
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: about twenty years in the myth | Statement: [Penelope, durationOfOdysseusAbsence, about twenty years in the myth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: durationOfOdysseusAbsence Context triple: [Penelope, durationOfOdysseusAbsence, about twenty years in the myth]
-
A.
missionDuration
Indicates the length of time over which a mission or operation takes place from start to finish.
-
B.
missionDurationToLastContact
Indicates the length of time from the mission’s start until the most recent (or final) communication contact.
-
C.
yearOfDisappearance
Indicates the specific year in which an entity disappeared or ceased to be present.
-
D.
timeInMyth
chosen
Indicates that an entity exists or occurs during a specific time period within a mythological narrative or tradition.
-
E.
missionDurationType
Indicates the classification of a mission’s length or time span (e.g., short-term, long-term, extended).
- 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_69a494267b4c819088c97a59182bf56a |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd53e4b48190abb2167f8074a6bc |
completed | March 1, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5844348190b01ac6506906ba3b |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.