Triple
T18879596
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julian Richards |
E461789
|
entity |
| Predicate | wrote |
P2831
|
FINISHED |
| Object | Darklands |
—
|
NE NERFINISHED |
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: Darklands | Statement: [Julian Richards, wrote, Darklands]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Darklands Context triple: [Julian Richards, wrote, Darklands]
-
A.
Darklands
chosen
Darklands is a 1996 British horror film directed by Julian Richards, often cited as an early example of the Celtic horror revival in UK cinema.
-
B.
Ghostlands
Ghostlands is a haunted, blood-elf–controlled zone in World of Warcraft, characterized by its dark, corrupted landscape bordering the elven homeland of Quel'Thalas.
-
C.
Dark Land
Dark Land is the final, lava-filled world ruled by Bowser in Super Mario Bros. 3, known for its high difficulty and fortress-heavy layout.
-
D.
Undying Lands
The Undying Lands are a blessed, immortal realm across the sea in J.R.R. Tolkien’s legendarium, serving as a final haven of peace and healing for Elves and a few chosen mortals.
-
E.
Shadowland
"Shadowland" is a powerful ballad from the stage adaptation of Disney's The Lion King, sung by Nala as she leaves her devastated homeland in search of help.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c3d06ef481908bba297d7a1fd011 |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 10, 2026, 11:57 a.m.