Triple
T23032447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liam Williams: Ladhood |
E573499
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Liam Williams |
—
|
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: Liam Williams | Statement: [Liam Williams: Ladhood, writer, Liam Williams]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liam Williams Context triple: [Liam Williams: Ladhood, writer, Liam Williams]
-
A.
Liam Williams
chosen
Liam Williams is a British comedian, writer, and actor known for his introspective, often melancholic humor and for creating and starring in the coming-of-age series "Ladhood."
-
B.
Gareth Williams
Gareth Williams is a Welsh former rugby union player who represented Wales internationally.
-
C.
Liam Smith
Liam Smith is a fictional character featured in the underwater-themed context of "Underwater."
-
D.
Liam Thomas
Liam Thomas is an actor known for appearing in the British political thriller film "Page Eight."
-
E.
Liam Bailey
Liam Bailey is a British singer-songwriter known for his soulful blend of reggae, R&B, and blues-influenced vocals.
- 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_69e245b911188190bc3d96326c847969 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f184822a90819081907d72c76770b0 |
completed | April 29, 2026, 4:09 a.m. |
Created at: April 17, 2026, 3:53 p.m.