Triple
T33319433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thundering Legion |
E853097
|
entity |
| Predicate | sizeApproximation |
P6061
|
FINISHED |
| Object | around 5,000–6,000 soldiers at full strength |
—
|
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: around 5,000–6,000 soldiers at full strength | Statement: [Thundering Legion, sizeApproximation, around 5,000–6,000 soldiers at full strength]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sizeApproximation Context triple: [Thundering Legion, sizeApproximation, around 5,000–6,000 soldiers at full strength]
-
A.
approximateSize
chosen
Indicates that one entity has a size that is roughly or approximately equal to the size of another entity.
-
B.
hasDimensionsApprox
Indicates that an entity has physical dimensions that are known only approximately, rather than as exact measurements.
-
C.
approximateWeightInPounds
Indicates the estimated weight of an entity expressed in pounds, rather than an exact measured value.
-
D.
rangeLengthApprox
Indicates that the length or extent of a range is approximately equal to a specified value, allowing for some tolerance or imprecision.
-
E.
heightEstimate
Indicates an estimated or approximate value for the height of an entity, rather than a precisely measured height.
- 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_69f349685f088190b8fda44083a018a9 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e3156ea48190b604e414665ef351 |
completed | May 3, 2026, 5:54 a.m. |
| PD | Predicate disambiguation | batch_69f6de0b9ba48190887c9eb5d06a2e94 |
completed | May 3, 2026, 5:32 a.m. |
Created at: May 1, 2026, 1:33 a.m.