Triple
T26790374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siwi people |
E670499
|
entity |
| Predicate | associatedWithOasis |
P2830
|
FINISHED |
| Object | Siwa Oasis |
—
|
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: Siwa Oasis | Statement: [Siwi people, associatedWithOasis, Siwa Oasis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithOasis Context triple: [Siwi people, associatedWithOasis, Siwa Oasis]
-
A.
associatedWithStand
Indicates a relationship where an entity is linked or connected to a particular stand, such as being located at, operating in, or otherwise related to that stand.
-
B.
isAssociatedWith
chosen
Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
-
C.
associatedWithPub
Indicates that an entity has a connection or relationship with a particular publication (e.g., as source, reference, or related work).
-
D.
associatedConsort
Indicates a spousal or consort relationship linking one entity to another as their partner.
-
E.
associatedWithSea
Indicates a relationship in which something has a connection, relevance, or linkage to the sea or marine environment.
- 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_69eeb31d45f8819089f52ebdbc556218 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69ff7595c9bc8190982c6e6e07a0c78f |
completed | May 9, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69ff715432a88190a25670d26614bde2 |
completed | May 9, 2026, 5:39 p.m. |
Created at: April 27, 2026, 4:16 a.m.