Triple
T10387596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deacon |
E244803
|
entity |
| Predicate | enemyOf |
P437
|
FINISHED |
| Object | Mariner |
E834422
|
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: Mariner | Statement: [Deacon, enemyOf, Mariner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mariner Context triple: [Deacon, enemyOf, Mariner]
-
A.
Mariner
chosen
The Mariner is the nautical-themed mascot representing the athletic teams of the College of Coastal Georgia.
-
B.
Slocum
Slocum is a surname of English origin borne by various notable individuals in fields such as sports, politics, and the military.
-
C.
Magellan spacecraft
The Magellan spacecraft was a NASA robotic probe launched in 1989 that used radar mapping to produce the first detailed global images of the surface of Venus.
-
D.
Voyager
Voyager is a class of high-speed diesel-electric multiple unit trains used for intercity passenger services in the United Kingdom.
-
E.
Voyager
Voyager is South African Airways’ loyalty program that rewards frequent flyers with miles redeemable for flights, upgrades, and other travel benefits.
- 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_69d381b5116081908d85227bab6d3c0c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9a59d688190b1da1ea0ed48fafa |
completed | April 7, 2026, 11:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d795aa3afc8190aed1ca11556ae34f |
completed | April 9, 2026, 12:03 p.m. |
Created at: April 6, 2026, 12:05 p.m.