Triple
T20025627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Daniel Z. Romualdez Airport |
E494973
|
entity |
| Predicate | isLocatedInBody |
P69956
|
FINISHED |
| Object | Philippine archipelago |
—
|
NE NERFINISHED |
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: Philippine archipelago | Statement: [Daniel Z. Romualdez Airport, isLocatedInBody, Philippine archipelago]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Philippine archipelago Context triple: [Daniel Z. Romualdez Airport, isLocatedInBody, Philippine archipelago]
-
A.
Philippine Archipelago
chosen
The Philippine Archipelago is a vast group of over 7,000 tropical islands in Southeast Asia, known for its rich biodiversity, complex geology, and location along the Pacific Ring of Fire.
-
B.
Chinijo Archipelago
The Chinijo Archipelago is a small, protected group of volcanic islands and islets off the northern coast of Lanzarote, known for its rich marine biodiversity and status as a major nature reserve.
-
C.
Kalayaan Island Group
The Kalayaan Island Group is a Philippine-claimed cluster of islands, islets, and reefs in the Spratly Islands area of the South China Sea, noted for its strategic and geopolitical significance.
-
D.
Malay Archipelago
The Malay Archipelago is the world’s largest group of islands, spanning between mainland Southeast Asia and Australia and encompassing modern nations such as Indonesia, the Philippines, and Malaysia.
-
E.
Kepulauan Sulu
Kepulauan Sulu is an archipelago in the southwestern Philippines, forming part of the Sulu Archipelago between Mindanao and Borneo and known for its strategic maritime location and diverse Muslim-majority communities.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLocatedInBody Context triple: [Daniel Z. Romualdez Airport, isLocatedInBody, Philippine archipelago]
-
A.
isInBody
chosen
Indicates that one entity is physically contained within or located inside the body of another entity.
-
B.
locatedOnBody
Indicates that one entity is physically situated on the surface or external part of another entity’s body.
-
C.
belongsToBody
Indicates that something is a part of, or under the ownership/authority of, a particular body or organization.
-
D.
isKeyBodyOf
Indicates that one entity serves as the primary or central body/content component of another entity.
-
E.
hasBodyRegion
Indicates that an entity possesses, includes, or is associated with a specific anatomical or bodily region.
- 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_69da626bfd288190aa5d65098b6433ae |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6628d5b8c8190a35f95ac4a016550 |
completed | April 20, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69e54ce752748190a0a1ffddd0372271 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:35 p.m.