Triple
T682331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imperial Estates |
E13208
|
entity |
| Predicate | existedFrom |
P10386
|
FINISHED |
| Object | late Middle Ages |
—
|
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: late Middle Ages | Statement: [Imperial Estates, existedFrom, late Middle Ages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: existedFrom Context triple: [Imperial Estates, existedFrom, late Middle Ages]
-
A.
establishedFrom
Indicates that something was created, founded, or formed starting from a specified source, origin, or prior entity.
-
B.
existsFor
Indicates that something is present, available, or holds true for a particular entity, context, or condition.
-
C.
historicalExistence
Indicates that an entity actually existed at some point in real-world history, as opposed to being fictional, hypothetical, or mythological.
-
D.
createdFor
Indicates that one entity was made, produced, or designed specifically to serve, benefit, or be used by another entity.
-
E.
attestedFrom
chosen
Indicates the earliest point in time or source from which something is documented, recorded, or evidenced as existing or in use.
- 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_69a4933e0f98819097d22766c49b61b8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a06f9ee88190a2d757aacd8e3f5b |
completed | March 1, 2026, 8:24 p.m. |
| PD | Predicate disambiguation | batch_69a49d1f0ccc819088c1527beabcb718 |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.