Triple
T37590225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Borrell II, Count of Barcelona and Urgell |
E935239
|
entity |
| Predicate | startTimeAsCountOfUrgell |
P203155
|
FINISHED |
| Object | 948 |
—
|
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: 948 | Statement: [Borrell II, Count of Barcelona and Urgell, startTimeAsCountOfUrgell, 948]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTimeAsCountOfUrgell Context triple: [Borrell II, Count of Barcelona and Urgell, startTimeAsCountOfUrgell, 948]
-
A.
endTimeAsCountOfUrgell
Indicates the point in time when something ends, expressed as a numerical count according to the Urgell-based time system.
-
B.
startTimeAsCardinal
Indicates the specific clock time at which an event or action begins, expressed as a cardinal (numeric) value rather than a textual or formatted time.
-
C.
endTimeRepresented
Indicates that a specified time value denotes the point at which an event, state, or representation concludes.
-
D.
startTimeAsRepresentative
Indicates the time at which an entity begins serving or acting in a representative capacity.
-
E.
durationUntil
Indicates the length of time remaining from a given starting point until a specified future event or state occurs.
- 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_69f76ecf39c081909baffe597bb55273 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a01295195748190b896d99c3d1f6134 |
completed | May 11, 2026, 12:56 a.m. |
| PD | Predicate disambiguation | batch_6a0128fe96dc8190a73715ab08752dd1 |
completed | May 11, 2026, 12:55 a.m. |
| PDg | Predicate description generation | batch_6a012950e8d48190a9dc1105fe7a5fb3 |
completed | May 11, 2026, 12:56 a.m. |
Created at: May 3, 2026, 4:18 p.m.