Triple
T4375659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Kumamoto Castle |
E98999
|
entity |
| Predicate | strengthDefenders |
P12310
|
FINISHED |
| Object | approximately 3,800 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: approximately 3,800 soldiers | Statement: [Siege of Kumamoto Castle, strengthDefenders, approximately 3,800 soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strengthDefenders Context triple: [Siege of Kumamoto Castle, strengthDefenders, approximately 3,800 soldiers]
-
A.
hasDefenderStrength
chosen
Indicates that an entity possesses a certain level or measure of defensive capability or protective power.
-
B.
defenderIn
Indicates that an entity serves as a defensive agent or protector within a specified context, situation, or domain.
-
C.
defender
Indicates a relationship where one entity protects, guards, or supports another entity against threats, attacks, or criticism.
-
D.
strengthType
Indicates the specific category or nature of strength associated with an entity or relationship (e.g., physical, structural, or conceptual strength).
-
E.
strengthDescription
Indicates a description or characterization of the degree of strength associated with an entity or relationship.
- 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_69b3454ea8f48190a49c2436624d6ef6 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b352222df48190bead639e99635faf |
completed | March 12, 2026, 11:54 p.m. |
| PD | Predicate disambiguation | batch_69b34f557fe8819085032bf7f0cea5dc |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:18 p.m.