Triple
T11221226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annabelle Wallis |
E265568
|
entity |
| Predicate | characterIn |
P12208
|
FINISHED |
| Object | Tag |
E645751
|
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: Tag | Statement: [Annabelle Wallis, characterIn, Tag]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tag Context triple: [Annabelle Wallis, characterIn, Tag]
-
A.
Tag
chosen
Tag is a 2018 American comedy film about a group of lifelong friends who engage in an elaborate, decades-long game of tag.
-
B.
TAG
TAG is the IATA airport code for Bohol–Panglao International Airport in the Philippines.
-
C.
TAG
TAG is the W3C Technical Architecture Group, a committee that steers the architectural principles and long-term technical direction of the World Wide Web.
-
D.
Tagged
Tagged is a social networking service known for its focus on meeting new people through social discovery features like games, profiles, and friend suggestions.
-
E.
Tagdemt
Tagdemt is a historic Algerian town best known as the former capital and stronghold of Emir Abdelkader during his 19th-century resistance against French colonial rule.
- 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_69d6aac59460819089b9848b27f57848 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8eb84c48190b4f3bede254afde2 |
completed | April 9, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4977cab4481909c6b94ca07cd5e4a |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 8, 2026, 9:30 p.m.