Triple
T8511805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Wisdom |
E201469
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Lightkeepers |
E710618
|
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 Lightkeepers | Statement: [Tom Wisdom, notableWork, The Lightkeepers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Lightkeepers Context triple: [Tom Wisdom, notableWork, The Lightkeepers]
-
A.
The Lightkeepers
chosen
The Lightkeepers is a film produced by Neal Dodson, best known as an independent producer of character-driven dramas and genre movies.
-
B.
The Light
The Light is a work by author W. Jeffrey, likely a novel or story centered on themes of illumination, revelation, or spiritual insight.
-
C.
The Light
The Light is a notable work by the rapper Common, showcasing his introspective lyricism and soulful, jazz-influenced hip-hop style.
-
D.
The Light
The Light is a chapter or section within the novel "Like Water for Chocolate," contributing to its blend of magical realism, romance, and culinary symbolism.
-
E.
The Last Lighthouse Keeper
"The Last Lighthouse Keeper" is a novel by British writer and broadcaster Alan Titchmarsh, blending romance and drama in a coastal setting.
- 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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe60b0d4c8190812ddbc1c17389c8 |
completed | March 31, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce4e47542c8190af93dca3ce16a04b |
completed | April 2, 2026, 11:08 a.m. |
Created at: March 30, 2026, 6:15 p.m.