Triple
T13044740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | English longbowmen |
E327287
|
entity |
| Predicate | couldPenetrate |
P60770
|
FINISHED |
| Object | mail armor |
—
|
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: mail armor | Statement: [English longbowmen, couldPenetrate, mail armor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: couldPenetrate Context triple: [English longbowmen, couldPenetrate, mail armor]
-
A.
couldPass
Indicates that one entity had the ability or potential to move through, overcome, or be accepted by another entity or barrier.
-
B.
cannot
Indicates that one entity lacks the ability, permission, or possibility to perform an action or participate in a specified relationship with another entity.
-
C.
canPass
Indicates that one entity is able or permitted to move through, cross, or successfully traverse another entity or barrier.
-
D.
attackFeasibility
chosen
Indicates the extent to which carrying out an attack is practically possible given current conditions, capabilities, and constraints.
-
E.
canTry
Indicates that an entity has the possibility or permission to attempt performing a particular action or achieving a certain outcome.
- 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_69d8076e64308190904fb5c93517c901 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d98a9829b48190b23624b6b3df4600 |
completed | April 10, 2026, 11:41 p.m. |
| PD | Predicate disambiguation | batch_69d9803aca4c8190b1015cd159cc47a9 |
completed | April 10, 2026, 10:56 p.m. |
Created at: April 9, 2026, 8:56 p.m.