Triple
T33319270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miracle of the Thundering Legion |
E853094
|
entity |
| Predicate | effectOnRomans |
P191820
|
FINISHED |
| Object | provided drinking water to the Roman soldiers |
—
|
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: provided drinking water to the Roman soldiers | Statement: [Miracle of the Thundering Legion, effectOnRomans, provided drinking water to the Roman soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnRomans Context triple: [Miracle of the Thundering Legion, effectOnRomans, provided drinking water to the Roman soldiers]
-
A.
stanceTowardRome
Indicates the nature or attitude of an entity’s position or policy in relation to Rome.
-
B.
eraOfRomanConquest
Indicates the historical period during which the Roman Empire conquered or brought the referenced entity under Roman control.
-
C.
statusAfterRomanConquest
Indicates the condition or standing of an entity following its conquest by the Roman state or Roman forces.
-
D.
aimOfRome
Indicates that something is the goal, purpose, or intended objective of Rome.
-
E.
casualtiesSideRomanEmpire
Indicates that the recorded casualties in a conflict or battle occurred on the side of the Roman Empire.
- 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_69f349685f088190b8fda44083a018a9 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
| PDg | Predicate description generation | batch_69fcec5e560481909cd710b88897e833 |
completed | May 7, 2026, 7:47 p.m. |
Created at: May 1, 2026, 1:33 a.m.