Triple
T147649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Normans |
E3365
|
entity |
| Predicate | militaryCharacteristic |
P7256
|
FINISHED |
| Object | heavy cavalry |
—
|
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: heavy cavalry | Statement: [Normans, militaryCharacteristic, heavy cavalry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryCharacteristic Context triple: [Normans, militaryCharacteristic, heavy cavalry]
-
A.
warfareCapability
Indicates the ability or capacity of an entity to engage in, conduct, or support acts of warfare.
-
B.
militaryProvision
Indicates the provision, allocation, or supply of military resources, services, or support from one entity to another.
-
C.
warfareType
Indicates the specific kind or category of warfare that characterizes a given conflict or military engagement.
-
D.
militaryStrategy
Indicates a relationship where an entity plans, directs, or is associated with the organized use of armed forces and tactics to achieve military or defense objectives.
-
E.
usedWarfareType
Indicates the specific type or method of warfare that an entity employed in a conflict or military 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_69a252868de4819080e21c9938bfe8b6 |
completed | Feb. 28, 2026, 2:27 a.m. |
| NER | Named-entity recognition | batch_69a258808ff08190a06b6206f635612b |
completed | Feb. 28, 2026, 2:52 a.m. |
| PD | Predicate disambiguation | batch_69a256580c2c8190beecca60ca8595f3 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2587e598c81909e1082b813971f48 |
completed | Feb. 28, 2026, 2:52 a.m. |
Created at: Feb. 28, 2026, 2:31 a.m.