Triple
T30752947
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tân Định Ward |
E783004
|
entity |
| Predicate | hasColorAssociatedLandmark |
P133091
|
FINISHED |
| Object | pink Tân Định Church |
—
|
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: pink Tân Định Church | Statement: [Tân Định Ward, hasColorAssociatedLandmark, pink Tân Định Church]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasColorAssociatedLandmark Context triple: [Tân Định Ward, hasColorAssociatedLandmark, pink Tân Định Church]
-
A.
hasColorOnRouteMap
Indicates that a specific color is used to represent an entity (such as a route or line) on a route map.
-
B.
hasLandmarkProperty
Indicates that something possesses a notable or defining landmark-related characteristic or feature.
-
C.
hasColorSymbol
Indicates that one entity is associated with another entity that serves as its representative or symbolic color.
-
D.
hasFacadeColorAssociation
chosen
Indicates an association between a building’s facade and a specific color or set of colors used on it.
-
E.
markerColor
Indicates the color attribute assigned to a given marker in the relationship.
- 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_69f224af8d8481908bea03890c5618be |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a018c6b7178819097d5450a1e3c2408 |
completed | May 11, 2026, 7:59 a.m. |
| PD | Predicate disambiguation | batch_6a018a4f741c8190babe721a908e2f5e |
completed | May 11, 2026, 7:50 a.m. |
Created at: April 29, 2026, 8:39 p.m.