Triple
T34654298
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bérenger Saunière |
E889930
|
entity |
| Predicate | startTimeOfTenureAtRennesLeChateau |
P202011
|
FINISHED |
| Object | 1885 |
—
|
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: 1885 | Statement: [Bérenger Saunière, startTimeOfTenureAtRennesLeChateau, 1885]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeOfTenureAtRennesLeChateau Context triple: [Bérenger Saunière, startTimeOfTenureAtRennesLeChateau, 1885]
-
A.
endTimeOfTenureAtRennesLeChateau
Indicates the point in time when an entity’s period of tenure at Rennes-le-Château comes to an end.
-
B.
RenePortlandTenureStart
Indicates the starting point in time when Rene Portland began her tenure in a particular role or position.
-
C.
RenePortlandTenureEnd
Indicates the time or event at which Rene Portland’s tenure or period in a particular role or position comes to an end.
-
D.
startTimeAsArchbishopOfReims
Indicates the date and time when an individual began their tenure serving as Archbishop of Reims.
-
E.
tenureAsEarlStart
Indicates the date or point in time when an individual’s tenure or period of holding the title of Earl begins.
- F. None of above. chosen
Provenance (4 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_69f349d906bc8190b2efd9eff237d94b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a0045a7b4c081908e4dedabda7cf790 |
completed | May 10, 2026, 8:45 a.m. |
| PD | Predicate disambiguation | batch_6a0042b148a48190974b173f352e4b7f |
completed | May 10, 2026, 8:32 a.m. |
| PDg | Predicate description generation | batch_6a0045a6ce788190913fa017097a15b8 |
completed | May 10, 2026, 8:45 a.m. |
Created at: May 1, 2026, 2:04 a.m.