Triple
T37544149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess of Pisa |
E933408
|
entity |
| Predicate | linkedToCultSite |
P136135
|
FINISHED |
| Object | Olympia |
—
|
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: Olympia | Statement: [Princess of Pisa, linkedToCultSite, Olympia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedToCultSite Context triple: [Princess of Pisa, linkedToCultSite, Olympia]
-
A.
associatedWithCultCenter
chosen
Indicates a relationship where something (such as a deity, object, or practice) is linked to, connected with, or primarily related to a specific cult center or place of worship.
-
B.
associatedWithCultObject
Indicates that an entity has a relationship or connection to a cult object, such as being used for, dedicated to, or symbolically linked with it.
-
C.
associatedCult
Indicates that an entity is connected or linked to a particular cult, typically through membership, affiliation, or influence.
-
D.
earlierCultOnSite
Indicates that a religious cult or worship practice existed at a location prior to the one currently under consideration.
-
E.
relatedToArchaeologicalSite
Indicates that one entity has a contextual, historical, or functional connection to an archaeological site.
- 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fef2db323c8190821bda53f22a42be |
completed | May 9, 2026, 8:39 a.m. |
| PD | Predicate disambiguation | batch_69fef21d63c88190abf6a99b59b3c655 |
completed | May 9, 2026, 8:36 a.m. |
Created at: May 3, 2026, 4:17 p.m.