Triple
T27342252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kota Belimbing |
E684136
|
entity |
| Predicate | productHighlight |
P3362
|
FINISHED |
| Object | starfruit from Depok |
—
|
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: starfruit from Depok | Statement: [Kota Belimbing, productHighlight, starfruit from Depok]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productHighlight Context triple: [Kota Belimbing, productHighlight, starfruit from Depok]
-
A.
featuresPromotion
Indicates that something includes, offers, or presents a promotion as part of its content or configuration.
-
B.
productCharacteristic
Indicates that a product possesses, exhibits, or is defined by a specific characteristic or attribute.
-
C.
brandFeatures
Indicates that a brand includes, offers, or is characterized by a particular feature or attribute.
-
D.
productIndication
Indicates that a product is intended, approved, or used for a particular purpose, condition, or application.
-
E.
highlights
chosen
Indicates that one entity draws special attention to, emphasizes, or visually marks another entity as important or noteworthy.
- 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_69ef1480a76481908684256ddd5bfda3 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f739a638748190808e7a2930dce16e |
completed | May 3, 2026, 12:03 p.m. |
| PD | Predicate disambiguation | batch_69f732f2dc6c8190a4e86da98cc5eb05 |
completed | May 3, 2026, 11:35 a.m. |
Created at: April 27, 2026, 11:43 a.m.