Triple
T12530506
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matthew |
E299549
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Luke |
unclear NED1
|
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: Luke | Statement: [Matthew, friend, Luke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luke Context triple: [Matthew, friend, Luke]
-
A.
Luke
Luke is a character portrayed by Chiwetel Ejiofor in the romantic comedy film "Love Actually."
-
B.
Luke
Luke is a central character in James Baldwin’s play "The Amen Corner," serving as the estranged husband whose return forces the protagonist and her church community to confront painful truths about faith, family, and hypocrisy.
-
C.
Luke
Luke is a small town located in Allegany County, Maryland, known historically for its paper mill industry.
-
D.
Luke
Luke is a fictional character associated with mosquitoes, likely appearing in a story or media where he interacts with or is defined by these insects.
-
E.
Luke
Luke is the central protagonist of the horror film "The Ritual," a grieving man who confronts both inner guilt and supernatural terror during a hiking trip in a Scandinavian forest.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d6ada5cdd48190860d9ce30aff69be |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d95469d100819087c83bc55e3ec9ce |
completed | April 10, 2026, 7:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f64bc674e881908673e1f9103cc8be |
completed | May 2, 2026, 7:08 p.m. |
Created at: April 8, 2026, 9:57 p.m.