Triple
T15891389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lynn Collins |
E385331
|
entity |
| Predicate | playedCharacter |
P1507
|
FINISHED |
| Object | Dejah Thoris |
E891044
|
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: Dejah Thoris | Statement: [Lynn Collins, playedCharacter, Dejah Thoris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dejah Thoris Context triple: [Lynn Collins, playedCharacter, Dejah Thoris]
-
A.
Dejah Thoris
chosen
Dejah Thoris is a Martian princess and scientist from Edgar Rice Burroughs' Barsoom series, portrayed as a key heroine and love interest in the film "John Carter."
-
B.
Shera
Shera is the anthropomorphic tiger mascot created to represent and promote the 2010 Commonwealth Games held in Delhi, India.
-
C.
Mara
The Mara is a malevolent, mind-controlling entity from the Doctor Who universe that haunts the dreams and fears of its victims, notably opposing the Fifth Doctor.
-
D.
Mara
"Mara" is a dark, atmospheric track by experimental electronic producer The Haxan Cloak, known for its ominous sound design and immersive, cinematic mood.
-
E.
Mara
Mara is a surname of Irish origin borne by various notable individuals in fields such as sports, entertainment, and politics.
- 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_69d86da5b800819083a31be937d738b0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1561e5ac481908ead7de3140c769d |
completed | April 16, 2026, 9:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb047b6248190b6c11ef20636f50f |
completed | May 9, 2026, 10:08 p.m. |
Created at: April 10, 2026, 4:51 a.m.