Triple
T10077548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Hebrides |
E213806
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Epi |
E150221
|
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: Epi | Statement: [New Hebrides, hasIsland, Epi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Epi Context triple: [New Hebrides, hasIsland, Epi]
-
A.
Epi
chosen
Epi is a volcanic island in central Vanuatu known for its lush landscapes, traditional villages, and surrounding coral reefs.
-
B.
Epip
Epip is a summer month in the Coptic calendar, roughly corresponding to July in the Gregorian calendar.
-
C.
EPI
EPI is the abbreviation for Exploding Plastic Inevitable, the multimedia performance series created by Andy Warhol that combined live music, film projections, and avant-garde art in the 1960s.
-
D.
EPI
EPI is a global public health initiative led by the World Health Organization that aims to ensure universal access to routine, life-saving vaccinations, particularly for children.
-
E.
EPOP
EPOP is the ICAO airport code assigned to Opole-Polska Nowa Wieś Airport, a Polish airfield primarily serving sports and general aviation.
- 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_69ca839bf730819086900c323c9b8c95 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd02f47e08190bfeb641b202beecc |
completed | April 2, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d29ad05bbc8190b103d66c9e786c86 |
completed | April 5, 2026, 5:24 p.m. |
Created at: March 30, 2026, 8:59 p.m.