Triple
T37130013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pulau Blakang Mati |
E919491
|
entity |
| Predicate | MatiMeaning |
P169138
|
FINISHED |
| Object | dead |
—
|
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: dead | Statement: [Pulau Blakang Mati, MatiMeaning, dead]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: MatiMeaning Context triple: [Pulau Blakang Mati, MatiMeaning, dead]
-
A.
oniMeaning
Indicates that one entity expresses or conveys the meaning or sense of another entity (such as a word, phrase, or symbol).
-
B.
ARMeaning
Indicates that an entity’s meaning, interpretation, or semantic content is being specified or defined in relation to another entity or context.
-
C.
MiriMeaning
Indicates that one entity conveys or expresses a particular meaning, sense, or significance with respect to another entity.
-
D.
namingMeaning
chosen
Indicates that one entity provides the meaning, sense, or semantic interpretation of a given name or naming expression for another entity.
-
E.
ermenMeaning
Indicates that one entity represents or conveys the meaning or semantic interpretation of 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_69f76e9d13e48190a108f7fbf80ff375 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:15 p.m.