Triple
T23630148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crossland family |
E583582
|
entity |
| Predicate | armsFeature |
P153339
|
FINISHED |
| Object | quartered design with red and white colors |
—
|
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: quartered design with red and white colors | Statement: [Crossland family, armsFeature, quartered design with red and white colors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armsFeature Context triple: [Crossland family, armsFeature, quartered design with red and white colors]
-
A.
greaterArmsFeature
Indicates that one entity possesses a more prominent or advanced arm-related feature than another entity.
-
B.
armorFeature
Indicates that one entity is a functional or descriptive feature of another entity’s armor.
-
C.
armsControl
Indicates a relationship where parties engage in limiting, regulating, or reducing weapons and military capabilities, often through agreements or treaties.
-
D.
handguardFeature
Indicates that an item possesses a specific characteristic, design element, or functional attribute related to its handguard component.
-
E.
hasArm
Indicates that one entity possesses or is equipped with an arm as a physical part or component of itself.
- 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_69e248fc8d74819091bd5baef2f36f6f |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b1e71cac8190a3e1c04d7a5fffa1 |
completed | April 29, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69f118d0e0588190a86527a7747c5427 |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f138b8c9248190b059bc38a9a50958 |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 17, 2026, 6:47 p.m.