Triple
T14212580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Look at Me |
E352266
|
entity |
| Predicate | isFollowedBy |
P134
|
FINISHED |
| Object | The Keep |
E352265
|
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: The Keep | Statement: [Look at Me, isFollowedBy, The Keep]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Keep Context triple: [Look at Me, isFollowedBy, The Keep]
-
A.
The Keep
chosen
The Keep is a 2006 novel by Jennifer Egan that blends gothic suspense with postmodern storytelling to explore memory, guilt, and the power of narrative.
-
B.
The Keep
The Keep is a 1983 supernatural horror film directed by Michael Mann, adapted from F. Paul Wilson’s novel about a mysterious fortress in World War II Romania.
-
C.
Stonekeep
Stonekeep is a 1995 first-person dungeon-crawling role-playing video game known for its digitized graphics, live-action cutscenes, and immersive fantasy setting.
-
D.
The Fortress
The Fortress is a popular nickname for MAPFRE Stadium, the historic soccer-specific home of the Columbus Crew in Major League Soccer.
-
E.
The Fortress
The Fortress is a South Korean historical drama film depicting the Joseon court’s struggle for survival during the Qing invasion, directed by Hwang Dong-hyuk.
- 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_69d8278a06e481908b5d6af0a8afe737 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de620dba0c8190bb77a1df10e1d3a7 |
completed | April 14, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd19574280819091bafd95a75983bf |
completed | May 7, 2026, 10:59 p.m. |
Created at: April 10, 2026, 1:05 a.m.