Triple
T17669605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham Spencer |
E440483
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Excite |
—
|
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: Excite | Statement: [Graham Spencer, employer, Excite]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Excite Context triple: [Graham Spencer, employer, Excite]
-
A.
Excite
chosen
Excite was a pioneering early web portal and search engine that played a major role in the first wave of consumer internet services in the 1990s.
-
B.
Excite@Q
Excite@Q is an interactive science and technology gallery at Questacon designed to engage visitors with hands-on exhibits and experiments.
-
C.
Lycos
Lycos is an early web search engine and internet portal that was popular in the 1990s alongside rivals like AltaVista and Yahoo.
-
D.
Flurry
Flurry is a mobile analytics and advertising platform known for providing app usage insights and monetization tools to developers.
-
E.
Zap
Zap is the energetic mascot character for the former WNBA team the Detroit Shock, known for entertaining fans at games with lively antics and team spirit.
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46f67f6188190a978c7c9f462064d |
completed | April 19, 2026, 6 a.m. |
Created at: April 10, 2026, 9:59 a.m.