Triple
T396591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Seal of the United States |
E8995
|
entity |
| Predicate | eagleHoldsInLeftTalon |
P5651
|
FINISHED |
| Object | bundle of 13 arrows |
—
|
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: bundle of 13 arrows | Statement: [Great Seal of the United States, eagleHoldsInLeftTalon, bundle of 13 arrows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eagleHoldsInLeftTalon Context triple: [Great Seal of the United States, eagleHoldsInLeftTalon, bundle of 13 arrows]
-
A.
canHold
Indicates that one entity has the capacity or ability to contain, support, or carry another entity.
-
B.
landingGear
Indicates that an entity’s landing gear is present, deployed, or otherwise involved in a landing-related state or action relative to another entity or context.
-
C.
eagleFaces
Indicates that an eagle is oriented toward, looking at, or facing another entity or direction.
-
D.
isUsuallyHeldBy
chosen
Indicates that something is most commonly or typically possessed, carried, or controlled by a particular entity.
-
E.
TTFirstHeld
Indicates that an entity held a particular title, position, or item for the first time in a given context or sequence.
- 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_69a2e7f55c60819097aff65ea2ca2832 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec8a941081909a152fda0ce24a98 |
completed | Feb. 28, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69a2e96d17d08190878d3a68b17d51ca |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.