Triple
T28933386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rio Tinto mining district |
E733847
|
entity |
| Predicate | wasMinedBy |
P6862
|
FINISHED |
| Object | Tartessians |
—
|
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: Tartessians | Statement: [Rio Tinto mining district, wasMinedBy, Tartessians]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasMinedBy Context triple: [Rio Tinto mining district, wasMinedBy, Tartessians]
-
A.
isMinedIn
Indicates that a resource or material is extracted or obtained from a particular location or site.
-
B.
minedOn
Indicates that a resource or material was extracted from a particular location or source on a specific date or time.
-
C.
minedSince
Indicates that a resource or material has been extracted from a location continuously starting from a specified point in time.
-
D.
minedBy
chosen
Indicates that a resource, material, or location is extracted or obtained through mining activities performed by a specified agent or entity.
-
E.
wasExtensivelyMinedIn
Indicates that a location or resource was subject to intensive or large-scale mining activity during a specified time or by a specified agent.
- 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_69f05b0b49b08190b8994b339c7980f6 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65b5453d0819082d3783b3b11019a |
completed | May 2, 2026, 8:15 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 8:30 a.m.