Triple
T30905157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman bridge of Paderne |
E787278
|
entity |
| Predicate | isGenerallyDatedTo |
P31438
|
FINISHED |
| Object | Middle Ages |
—
|
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: Middle Ages | Statement: [Roman bridge of Paderne, isGenerallyDatedTo, Middle Ages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isGenerallyDatedTo Context triple: [Roman bridge of Paderne, isGenerallyDatedTo, Middle Ages]
-
A.
traditionallyDated
chosen
Indicates that something is assigned a date based on traditional or customary chronology rather than on firmly established historical or scientific evidence.
-
B.
artifactsDatedTo
Indicates that certain artifacts have been assigned or associated with a specific date or time period.
-
C.
dateApproximate
Indicates that the associated date is not exact but estimated or approximate rather than precisely known.
-
D.
usedToDate
Indicates that two entities were previously in a romantic or dating relationship but are no longer together.
-
E.
تاريخ الميلاد التقريبي
Indicates an approximate or estimated date of birth for an entity, rather than an exact known birth date.
- 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_69f224bcbcb48190836df847424e4057 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6927ecf6c81908f9a9b1380bc43fe |
completed | May 3, 2026, 12:10 a.m. |
| PD | Predicate disambiguation | batch_69f68b7ec098819080480998038de940 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:50 p.m.