Triple
T12575002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman Ramp trail |
E300183
|
entity |
| Predicate | basedOnStructureBuiltBy |
P42422
|
FINISHED |
| Object | Roman forces |
—
|
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 forces | Statement: [Roman Ramp trail, basedOnStructureBuiltBy, Roman forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basedOnStructureBuiltBy Context triple: [Roman Ramp trail, basedOnStructureBuiltBy, Roman forces]
-
A.
builtStructureFor
Indicates that one entity constructed or assembled a structure specifically intended for the use, benefit, or purpose of another entity.
-
B.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
C.
structureTypeBuilt
Indicates the type or kind of structure that was constructed in a building or creation event.
-
D.
builtFrom
Indicates that one entity is constructed, composed, or formed using another entity as its material, component, or source.
-
E.
createdByConstructionOf
chosen
Indicates that something comes into existence as a result of a construction process or building activity performed by an agent.
- 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_69d7bde87b648190bcd0266e9efde098 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9550d84908190aea0f50055f6d92e |
completed | April 10, 2026, 7:52 p.m. |
| PD | Predicate disambiguation | batch_69d95414692881909c52a1de7d224b44 |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 9, 2026, 4:46 p.m.