Triple
T22459963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samuel Gibbs |
E555202
|
entity |
| Predicate | hasFamilyName |
P18
|
FINISHED |
| Object | Gibbs |
—
|
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: Gibbs | Statement: [Samuel Gibbs, hasFamilyName, Gibbs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gibbs Context triple: [Samuel Gibbs, hasFamilyName, Gibbs]
-
A.
Gibbs
chosen
Gibbs is a common English surname borne by various notable individuals across fields such as sports, science, and entertainment.
-
B.
Gibb
Gibb is the surname of Barry Gibb, the British-Australian singer, songwriter, and co-founder of the Bee Gees.
-
C.
Jibbs
Jibbs is an American rapper best known for his mid-2000s hit single "Chain Hang Low."
-
D.
Gibb-Galuten-Richardson
Gibb-Galuten-Richardson was a prominent late-1970s pop production team featuring Barry Gibb, Albhy Galuten, and Karl Richardson, known for crafting a string of hit records associated with the Bee Gees and their collaborators.
-
E.
Gib
Gib is a supporting character in the action-comedy film "True Lies," serving as Harry Tasker's tech-savvy and wisecracking partner in the secret government agency.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b7eb5688190bd5e41d4d8189668 |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.