Triple
T11591994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iloilo |
E274903
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Antique |
E235988
|
NE 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: Antique | Statement: [Iloilo, borders, Antique]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Antique Context triple: [Iloilo, borders, Antique]
-
A.
Antique
chosen
Antique is a coastal province in the Western Visayas region of the Philippines, known for its rugged mountains, hot springs, and rich cultural traditions.
-
B.
Old East
Old East is a historic University of North Carolina at Chapel Hill residence hall, widely regarded as the oldest state university building in the United States.
-
C.
Antiguoko
Antiguoko is a Spanish youth football club known for developing talented players who go on to professional careers.
-
D.
Olden
Olden is a surname most notably associated with Charles Smith Olden, a 19th-century American politician who served as Governor of New Jersey.
-
E.
Old
"Old" is a 2021 psychological horror thriller film written and directed by M. Night Shyamalan about a family on a secluded beach where rapid aging turns a single day into a lifetime.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aae6b14c81908dc5a74bad7591f9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8946594348190935106132fd18028 |
completed | April 10, 2026, 6:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ee86f246848190a5b020c3e05d02dd |
completed | April 26, 2026, 9:43 p.m. |
Created at: April 8, 2026, 9:38 p.m.