Triple
T17286559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coat of arms of the Philippines |
E419668
|
entity |
| Predicate | dexterHalf |
P73313
|
FINISHED |
| Object | American bald eagle displayed |
—
|
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: American bald eagle displayed | Statement: [Coat of arms of the Philippines, dexterHalf, American bald eagle displayed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dexterHalf Context triple: [Coat of arms of the Philippines, dexterHalf, American bald eagle displayed]
-
A.
rightHalfFeatures
chosen
Indicates that the associated features pertain specifically to the right half of an object, image, or spatial region.
-
B.
halves
Indicates that one quantity is exactly half the size, value, or amount of another.
-
C.
leftHalfFeatures
Indicates that the specified features pertain to, are located in, or are derived from the left half of an object, scene, or entity.
-
D.
isInHalf
Indicates that one entity is located within or belongs to a specified half or subdivision of another entity.
-
E.
Xtra
Indicates that one entity provides or possesses an additional or extra amount, feature, or benefit in relation to another 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e4378024988190aac6aec006f8f7a1 |
completed | April 19, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69e3b0118ad08190b119cd219c68ba67 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:40 a.m.