Triple
T3028435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krak des Chevaliers |
E82835
|
entity |
| Predicate | garrisonCapacity |
P13142
|
FINISHED |
| Object | around 2,000 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: around 2,000 soldiers | Statement: [Krak des Chevaliers, garrisonCapacity, around 2,000 soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: garrisonCapacity Context triple: [Krak des Chevaliers, garrisonCapacity, around 2,000 soldiers]
-
A.
garrisonSize
chosen
Indicates the number of troops or defenders stationed at a particular location as its garrison.
-
B.
garrisonType
Indicates the specific kind or classification of military garrison associated with an entity.
-
C.
garrisonOrHQ
Indicates that an entity serves as a military garrison or headquarters location for another entity.
-
D.
garrisonedForce
Indicates that a military force is stationed in and occupies a specific location, typically for defense or control.
-
E.
garrisonLabel
Indicates the designation or identifying label assigned to a military garrison associated with an entity.
- 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_69ad8b21a62881908ec5dd4fba4a187c |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9abea8f4819090554d7319778170 |
completed | March 8, 2026, 3:50 p.m. |
| PD | Predicate disambiguation | batch_69ad961e2a408190afb1759132701305 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.