Triple
T9815346
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tongeren |
E238388
|
entity |
| Predicate | hasTypeOfFortification |
P22477
|
FINISHED |
| Object | Roman walls |
—
|
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: Roman walls | Statement: [Tongeren, hasTypeOfFortification, Roman walls]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfFortification Context triple: [Tongeren, hasTypeOfFortification, Roman walls]
-
A.
isFortifiedWith
Indicates that one entity has been strengthened, enriched, or supplemented by the addition of another entity.
-
B.
hasFortifications
chosen
Indicates that one entity possesses or is equipped with defensive structures or fortification works associated with it.
-
C.
isFortifiedCity
Indicates that a city is strengthened with defensive structures or fortifications, such as walls, ramparts, or similar protective works.
-
D.
wasFortifiedBy
Indicates that a place or structure received defensive strengthening or fortification through the actions or resources of a specified agent or entity.
-
E.
fortType
Indicates the specific kind or classification of a fort associated with an entity.
- 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_69ca84dfde1481909f47c286d715f892 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb2f341648190bf8343e1124085cb |
completed | April 2, 2026, 12:06 a.m. |
| PD | Predicate disambiguation | batch_69cd03e01ea881909a7d93fc3994ace5 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:30 p.m.