Triple
T15606084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean d’Aire |
E375163
|
entity |
| Predicate | portrayedAsHolding |
P21131
|
FINISHED |
| Object | large keys of the city |
—
|
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: large keys of the city | Statement: [Jean d’Aire, portrayedAsHolding, large keys of the city]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedAsHolding Context triple: [Jean d’Aire, portrayedAsHolding, large keys of the city]
-
A.
depictedHolding
chosen
Indicates that one entity is shown in an image or representation as physically holding or grasping another entity.
-
B.
heldAs
Indicates that one entity is kept, maintained, or regarded in a particular state, role, or condition by another entity.
-
C.
heldAround
Indicates that one entity is held in a way that surrounds or encircles another entity.
-
D.
hasHolding
Indicates that one entity possesses, controls, or maintains ownership or custody of another entity as an asset or item.
-
E.
frontHeldBy
Indicates that the front side or leading part of an object is being physically supported or grasped by 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_69d85ccf2794819096cda4cbcb02d478 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e7d9328819090e93d55881269a5 |
completed | April 16, 2026, 2:50 a.m. |
| PD | Predicate disambiguation | batch_69deda844af081909e658ebc9d9b403d |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:12 a.m.