Triple
T7712157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ithaca |
E174784
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Frikes |
E99149
|
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: Frikes | Statement: [Ithaca, hasPort, Frikes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frikes Context triple: [Ithaca, hasPort, Frikes]
-
A.
Frikes
chosen
Frikes is a small coastal village and fishing harbor on the Greek island of Ithaca, known for its traditional tavernas and scenic bay.
-
B.
Fanatikerne
Fanatikerne is a notable painting by Norwegian artist Adolph Tidemand depicting religious zealots in a dramatic, realist style.
-
C.
Dweebs
Dweebs is a short-lived 1990s American sitcom about a group of socially awkward computer geeks working at a tech company.
-
D.
Kaniacs
Kaniacs are the dedicated fan community of American actor and musician Christian Kane, known for passionately supporting his film, television, and music projects.
-
E.
The Freak
The Freak is the nickname of Tim Lincecum, a former San Francisco Giants pitcher known for his dominant performances, unorthodox delivery, and multiple Cy Young Awards.
- 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_69c6995c463c8190a14458036249d419 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c702ae8b20819096930fe4be41b7be |
completed | March 27, 2026, 10:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8accffffc8190b307ad4741e688a8 |
completed | March 29, 2026, 4:38 a.m. |
Created at: March 27, 2026, 4:04 p.m.