Triple
T9679646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghost Stories |
E234247
|
entity |
| Predicate | single |
P3283
|
FINISHED |
| Object | Ink |
E813343
|
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: Ink | Statement: [Ghost Stories, single, Ink]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ink Context triple: [Ghost Stories, single, Ink]
-
A.
Ink
chosen
"Ink" is a song featured on the Japanese rock band Ghost Stories' album.
-
B.
Inkster
Inkster is a small rural municipality located in Grand Forks County in the U.S. state of North Dakota.
-
C.
Inkopolis
Inkopolis is a vibrant, ink-splattered metropolis and central hub world in the Splatoon video game series, where Inklings and Octolings gather for battles, shopping, and social activities.
-
D.
The Inkwell
The Inkwell is a 1994 coming-of-age comedy-drama film set during a family summer vacation on Martha’s Vineyard, known for its exploration of Black middle-class life in the 1970s.
-
E.
Ink (2017)
Ink (2017) is a stage play by James Graham that dramatizes the rise of Rupert Murdoch’s The Sun newspaper in 1960s Britain.
- 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_69ca84c99e34819092e5563a7106cfca |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9c9c586c8190abc0ab1771bf6c5c |
completed | April 1, 2026, 10:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d190fd1ad48190980e7bc3245046dc |
completed | April 4, 2026, 10:30 p.m. |
Created at: March 30, 2026, 8:16 p.m.