Triple
T17200407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Pydna (168 BC) |
E417458
|
entity |
| Predicate | approxMacedonianStrength |
P126381
|
FINISHED |
| Object | around 40,000–44,000 men |
—
|
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 40,000–44,000 men | Statement: [Battle of Pydna (168 BC), approxMacedonianStrength, around 40,000–44,000 men]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approxMacedonianStrength Context triple: [Battle of Pydna (168 BC), approxMacedonianStrength, around 40,000–44,000 men]
-
A.
MacedonianName
Indicates that an entity has a name expressed in the Macedonian language or in a Macedonian-specific form.
-
B.
strengthSerbia
Indicates the relative military, political, or economic power or influence associated with Serbia in a given context.
-
C.
languageNameMacedonian
Indicates that the specified name is the name of the Macedonian language.
-
D.
strengthBulgaria
Indicates a relationship where something possesses or demonstrates strength specifically associated with Bulgaria.
-
E.
strengthRussoAustrian
Indicates the relative military or political strength between Russian and Austrian forces or interests in a given context.
- 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_69d886d6ba8c819093215917b3d01689 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42daf2e5c81909c97d2e7a3ed7b88 |
completed | April 19, 2026, 1:19 a.m. |
| PD | Predicate disambiguation | batch_69e3831e354881908c5505ffd15c84e9 |
completed | April 18, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69e3873f62108190966c4e741ebd548d |
completed | April 18, 2026, 1:29 p.m. |
Created at: April 10, 2026, 5:38 a.m.