Triple
T31736943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graffiti House |
E810023
|
entity |
| Predicate | hasWallContent |
P180899
|
FINISHED |
| Object | drawings of soldiers and military symbols |
—
|
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: drawings of soldiers and military symbols | Statement: [Graffiti House, hasWallContent, drawings of soldiers and military symbols]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWallContent Context triple: [Graffiti House, hasWallContent, drawings of soldiers and military symbols]
-
A.
hasWall
Indicates that one entity possesses, includes, or is bounded by a wall.
-
B.
hasWallLayer
Indicates that one entity includes or is associated with a specific layer within a wall structure.
-
C.
hasWallText
Indicates that an entity features or is associated with text displayed on a wall, such as inscriptions, labels, or written information.
-
D.
hasWallType
Indicates the specific kind or classification of wall associated with an entity.
-
E.
hasWallRequirement
Indicates that an entity must satisfy a specified condition or standard related to walls (e.g., presence, type, or characteristics of walls).
- 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_69f348e0e4908190a884582eca646fb7 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
| PDg | Predicate description generation | batch_69f75788d40c819083bf2567b3091585 |
completed | May 3, 2026, 2:11 p.m. |
Created at: April 30, 2026, 11:23 p.m.