Triple
T34439653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 4 (Changi Airport) |
E884061
|
entity |
| Predicate | hasLandsideArea |
P199399
|
FINISHED |
| Object | arrival hall |
—
|
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: arrival hall | Statement: [Terminal 4 (Changi Airport), hasLandsideArea, arrival hall]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLandsideArea Context triple: [Terminal 4 (Changi Airport), hasLandsideArea, arrival hall]
-
A.
hasLandsideConnection
Indicates that two locations are connected by a route or access on land, allowing movement between them without using air or water transport.
-
B.
hasLandmarkArea
Indicates that a specified area is designated as the landmark area associated with a particular entity or location.
-
C.
hasAreaType
Indicates that an entity is associated with a specific kind or classification of area (e.g., urban, rural, coastal).
-
D.
hasStandingArea
Indicates that an entity includes or provides a designated area where people can stand.
-
E.
acquiredLandArea
Indicates the total area of land that has been obtained or taken possession of through an acquisition.
- F. None of above. chosen
Provenance (4 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_69f349c548d88190978e2a82502c03d0 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff370698ec81909bb1596d7d4112ba |
completed | May 9, 2026, 1:30 p.m. |
| PD | Predicate disambiguation | batch_69ff3699b6288190b564839cb05f5cf6 |
completed | May 9, 2026, 1:28 p.m. |
| PDg | Predicate description generation | batch_69ff3705e424819090ad7423ceefa506 |
completed | May 9, 2026, 1:30 p.m. |
Created at: May 1, 2026, 2 a.m.