Triple
T32209592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Franchthi Cave |
E822762
|
entity |
| Predicate | hasEarliestOccupationPeriod |
P77435
|
FINISHED |
| Object | Upper Paleolithic |
—
|
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: Upper Paleolithic | Statement: [Franchthi Cave, hasEarliestOccupationPeriod, Upper Paleolithic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEarliestOccupationPeriod Context triple: [Franchthi Cave, hasEarliestOccupationPeriod, Upper Paleolithic]
-
A.
earliestOccupationPeriod
chosen
Indicates the time period during which an entity was first occupied or used, before any later occupation periods.
-
B.
earliestKnownPeriod
Indicates the earliest historical or temporal period in which the subject is known or documented to have existed, occurred, or been relevant.
-
C.
earliestOccupationDate
Indicates the earliest known date on which an entity began a particular occupation or role.
-
D.
hasEarliestMajorCorpus
Indicates that one entity is associated with the earliest significant or primary body of work (major corpus) relative to other comparable entities.
-
E.
earliestMajorOccupation
Indicates the earliest significant occupation or professional role held by an entity in its life or career timeline.
- 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_69f3490a3bec819097bc58d4731b9d08 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bb91c24481908bec766e2ed19345 |
completed | May 3, 2026, 3:05 a.m. |
| PD | Predicate disambiguation | batch_69f6b3aa892481908d29283a074e6722 |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:37 a.m.