Triple
T5251626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. 3rd Armored Division |
E118600
|
entity |
| Predicate | distinctiveUnitInsignia |
P21497
|
FINISHED |
| Object | triangular shield with tank tread and thunderbolt |
—
|
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: triangular shield with tank tread and thunderbolt | Statement: [U.S. 3rd Armored Division, distinctiveUnitInsignia, triangular shield with tank tread and thunderbolt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distinctiveUnitInsignia Context triple: [U.S. 3rd Armored Division, distinctiveUnitInsignia, triangular shield with tank tread and thunderbolt]
-
A.
rankInsigniaWornOn
Indicates the physical location on a uniform or body where a rank insignia is displayed or attached.
-
B.
heraldicDivision
Indicates the way a heraldic shield or field is partitioned into distinct sections or areas.
-
C.
hasMilitaryDesignation
Indicates that an entity is assigned a specific military-related code, title, or classification.
-
D.
symbolOnInsignia
chosen
Indicates that a particular symbol appears on or is featured as part of an insignia.
-
E.
aircraftMarking
Indicates a relationship where a marking, symbol, or identifier is applied to or displayed on an aircraft.
- 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_69bd446978108190bb5f9c5c23d93f88 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b7b840881908bb1ecb8a0047382 |
completed | March 20, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69bd77c30bac8190a883ca45da35d667 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:50 p.m.