Triple
T17293738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reminiscence |
E419851
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Mae |
E918023
|
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: Mae | Statement: [Reminiscence, mainCharacter, Mae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mae Context triple: [Reminiscence, mainCharacter, Mae]
-
A.
Mae
Mae is a small settlement located on Namu Atoll in the Marshall Islands, a remote Pacific island nation.
-
B.
Mae
Mae is the given name of Maeby Fünke, a fictional character from the television series "Arrested Development."
-
C.
Mae
chosen
Mae is a mysterious, alluring young vampire who lures the protagonist into an outlaw bloodsucking clan in the 1987 cult horror film "Near Dark."
-
D.
Mae
Mae is an American alternative rock band known for their melodic sound and emotionally driven lyrics, which gained prominence in the 2000s indie and Christian rock scenes.
-
E.
Mae
Mae is a feminine given name, often used as a diminutive or variant of names like Mary or Margaret.
- 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_69d886db32608190a61e18862c5a8af6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e43785383881908ec61ddf5e2193cf |
completed | April 19, 2026, 2:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180d66bb8819086eb2c72b4dcbafb |
completed | May 11, 2026, 7:10 a.m. |
Created at: April 10, 2026, 5:40 a.m.