Triple
T32145400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manilatown |
E821009
|
entity |
| Predicate | centralLandmark |
P28850
|
FINISHED |
| Object | International Hotel |
—
|
NE NERFINISHED |
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: International Hotel | Statement: [Manilatown, centralLandmark, International Hotel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centralLandmark Context triple: [Manilatown, centralLandmark, International Hotel]
-
A.
hasCentralLandmark
chosen
Indicates that a place or area contains a primary or defining landmark located at or near its center.
-
B.
centralLocation
Indicates that one entity serves as the primary or central place associated with another entity.
-
C.
centralPeak
Indicates that one entity is the central, elevated peak located near the middle of another entity, typically within a larger structure such as a crater or basin.
-
D.
centerIs
Indicates that one entity serves as the central point or middle position of another entity or space.
-
E.
centralIsland
Indicates that one entity is an island located at or near the central region of another geographic or spatial context.
- 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_69f3490520d081909b2f1271dab75faa |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
Created at: May 1, 2026, 12:31 a.m.