Triple
T4479917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ramon Berenguer IV, Count of Barcelona |
E100102
|
entity |
| Predicate | reignStartAsPrinceOfAragon |
P56801
|
FINISHED |
| Object | 1137 |
—
|
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: 1137 | Statement: [Ramon Berenguer IV, Count of Barcelona, reignStartAsPrinceOfAragon, 1137]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reignStartAsPrinceOfAragon Context triple: [Ramon Berenguer IV, Count of Barcelona, reignStartAsPrinceOfAragon, 1137]
-
A.
startTimeAsKingOfAragon
Indicates the point in time when an entity began its reign as King of Aragon.
-
B.
reignStartAsKingOfPortugal
Indicates the time or event at which an individual begins their reign as the king of Portugal.
-
C.
reignStart
Indicates the date or point in time when an entity’s period of ruling or governing authority begins.
-
D.
reignAsCoRulerStart
Indicates the time or event when an entity begins to exercise ruling authority jointly with one or more other rulers.
-
E.
reignEndAsQueenOfAragon
Indicates the time or event at which an individual’s period of ruling as Queen of Aragon comes to an end.
- 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_69b34553cbe48190afa8ac1cac285b86 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35728ed508190ba0e882fa62d8848 |
completed | March 13, 2026, 12:15 a.m. |
| PD | Predicate disambiguation | batch_69b3563d63008190816e37027e761375 |
completed | March 13, 2026, 12:11 a.m. |
| PDg | Predicate description generation | batch_69b35727a8ac819090420bd3e2cfbcf1 |
completed | March 13, 2026, 12:15 a.m. |
Created at: March 12, 2026, 11:35 p.m.