Triple
T26295599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Merdeka Square |
E661406
|
entity |
| Predicate | hasRoadAround |
P93805
|
FINISHED |
| Object |
Jalan Medan Merdeka Utara
Jalan Medan Merdeka Utara is a major road forming the northern boundary of Merdeka Square in central Jakarta, Indonesia.
|
E1719212
|
NE FINISHED |
How this triple was built (3 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: Jalan Medan Merdeka Utara | Statement: [Merdeka Square, hasRoadAround, Jalan Medan Merdeka Utara]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Jalan Medan Merdeka Utara Triple: [Merdeka Square, hasRoadAround, Jalan Medan Merdeka Utara]
Generated description
Jalan Medan Merdeka Utara is a major road forming the northern boundary of Merdeka Square in central Jakarta, Indonesia.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoadAround Context triple: [Merdeka Square, hasRoadAround, Jalan Medan Merdeka Utara]
-
A.
hasRoads
chosen
Indicates that there exist constructed road connections linking the related entities.
-
B.
hasRoadway
Indicates that one location or area is connected to another by a road or roadway infrastructure.
-
C.
hasRoadComponent
Indicates that something includes, contains, or is composed of a specific road-related part or element.
-
D.
hasRoadPass
Indicates that an entity possesses a valid authorization or permit required to use a specific road or road network.
-
E.
hasRoadAbove
Indicates that one road segment is physically located above another, such as on an overpass, bridge, or elevated structure.
- F. None of above.
Provenance (6 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_69ee812cd48c81908054068f545f0526 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a118fc7fefc819099631a79e9e7a283 |
completed | May 23, 2026, 11:30 a.m. |
| NEDg | Description generation | batch_6a1190549934819082b10e07b035a7b9 |
completed | May 23, 2026, 11:32 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a11928405ac81908559a169b90f04a8 |
completed | May 23, 2026, 11:41 a.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 26, 2026, 10:11 p.m.