Triple
T5893144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ottoman army caught while crossing the Tisa River |
E131037
|
entity |
| Predicate | hasMethodOfCrossing |
P67174
|
FINISHED |
| Object | pontoon bridge |
—
|
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: pontoon bridge | Statement: [Ottoman army caught while crossing the Tisa River, hasMethodOfCrossing, pontoon bridge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMethodOfCrossing Context triple: [Ottoman army caught while crossing the Tisa River, hasMethodOfCrossing, pontoon bridge]
-
A.
hasBridgeTypeCrossing
Indicates that a bridge is characterized by a specific type of crossing it provides or supports.
-
B.
hasCross
Indicates that one entity possesses, displays, or is marked by a cross in relation to another entity or context.
-
C.
crossingOf
Indicates that one entity serves as the intersection or crossing point of two or more linear features, such as roads, paths, or tracks.
-
D.
hasAlternativeCrossing
Indicates that there exists another available crossing option that can be used instead of the primary one.
-
E.
hasBridgeTo
Indicates that one entity is connected to another by a bridge or bridging structure that allows passage or linkage between them.
- F. None of above. chosen
Provenance (4 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_69c00857439c819095950754176aa58a |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0400f1af881908d376ea4793f6dea |
completed | March 22, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69c0334dc8248190b7394dcece362d52 |
completed | March 22, 2026, 6:22 p.m. |
| PDg | Predicate description generation | batch_69c0400dbec08190b2ef73689b2c0c31 |
completed | March 22, 2026, 7:16 p.m. |
Created at: March 22, 2026, 3:58 p.m.