Triple
T28846722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman city walls of Trier |
E728472
|
entity |
| Predicate | partlyDestroyed |
P23714
|
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 city walls of Trier, partlyDestroyed, Middle Ages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partlyDestroyed Context triple: [Roman city walls of Trier, partlyDestroyed, Middle Ages]
-
A.
partiallyDestroyed
chosen
Indicates that an entity has been damaged or ruined to a significant extent but not completely destroyed.
-
B.
partiallyDestroyedByFire
Indicates that an entity has been damaged to some extent, but not completely destroyed, as a result of a fire.
-
C.
partlyDismantledBy
Indicates that an entity has been only partially taken apart, removed, or deconstructed by another agent or process.
-
D.
partlyRebuilt
Indicates that an entity has been reconstructed or restored to some extent, but not fully.
-
E.
partiallyRestored
Indicates that an entity has been brought back toward a previous or original state, but the restoration is incomplete or only partially achieved.
- 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_69f0319e8e7c8190b37288c8845b9dbc |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6645ba71c81908044ade6ab577018 |
completed | May 2, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f663362c008190a22afed262f1e426 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 6:42 a.m.