Triple
T9968313
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoff Johns |
E195738
|
entity |
| Predicate | workedOn |
P3
|
FINISHED |
| Object | Arrow (TV series) |
E149849
|
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: Arrow (TV series) | Statement: [Geoff Johns, workedOn, Arrow (TV series)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arrow (TV series) Context triple: [Geoff Johns, workedOn, Arrow (TV series)]
-
A.
Black Arrow
Black Arrow is the famed enchanted arrow in J.R.R. Tolkien's "The Hobbit" that Bard the Bowman uses to slay the dragon Smaug.
-
B.
Arrow
Arrow is the English translation of "Freccia," the nickname of the Italian World War II fighter aircraft Fiat G.50.
-
C.
Arrow
Arrow is a common English surname borne by various individuals, including the influential economist Kenneth Arrow.
-
D.
Arrow
chosen
Arrow is a popular American superhero television series based on the DC Comics character Green Arrow, known for launching the interconnected "Arrowverse" franchise.
-
E.
Arrow
Arrow is a regional passenger rail service brand used for trains operating between San Bernardino and Redlands in Southern California.
- 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_69ca82ebd1288190912f9e4482d1fa35 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb7b683ac8190ac97bd775a860d29 |
completed | April 2, 2026, 12:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d23db701b881909bb986a32df4349b |
completed | April 5, 2026, 10:47 a.m. |
Created at: March 30, 2026, 8:47 p.m.