Triple
T24779414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hardknott Roman Fort |
E619949
|
entity |
| Predicate | usedAgain |
P91997
|
FINISHED |
| Object | early 3rd century AD |
—
|
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: early 3rd century AD | Statement: [Hardknott Roman Fort, usedAgain, early 3rd century AD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAgain Context triple: [Hardknott Roman Fort, usedAgain, early 3rd century AD]
-
A.
usedBefore
Indicates that one entity was utilized or applied prior to the use or occurrence of another entity.
-
B.
usedOver
Indicates that one entity has been utilized, applied, or consumed in relation to another entity, typically as a resource, medium, or tool in a particular context or period.
-
C.
subsequentUse
Indicates that one entity is used, applied, or consumed after another entity in time or sequence.
-
D.
reusedIn
chosen
Indicates that something previously used in one context or instance is used again in another context or instance.
-
E.
usedDuring
Indicates that one entity is employed, applied, or active in the course of another entity’s process, event, or time period.
- 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_69e2fabdbe8c8190adbb9434b8636cad |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d6ef33081908f5d36ba1ae5f473 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 4:43 a.m.