Triple
T1179075
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Falkirk |
E25093
|
entity |
| Predicate | AntonineWallType |
P17521
|
FINISHED |
| Object | Roman frontier fortification |
—
|
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 frontier fortification | Statement: [Falkirk, AntonineWallType, Roman frontier fortification]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AntonineWallType Context triple: [Falkirk, AntonineWallType, Roman frontier fortification]
-
A.
fortressBuiltUnder
Indicates that one structure or location was constructed directly beneath or within the protective area of a fortress.
-
B.
arcTrenchSystem
Indicates a geological relationship where an oceanic trench is associated with and typically parallels a volcanic island arc as part of a subduction zone system.
-
C.
castleBuiltFor
Indicates that a castle was constructed specifically for the benefit, use, or commission of a particular person, group, or purpose.
-
D.
garrisonType
chosen
Indicates the specific kind or classification of military garrison associated with an entity.
-
E.
hasBorderWallOrFence
Indicates that a physical barrier such as a wall or fence exists along the border between two entities.
- 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_69a494267b4c819088c97a59182bf56a |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd53e4b48190abb2167f8074a6bc |
completed | March 1, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5844348190b01ac6506906ba3b |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.