Triple
T6102684
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Killing Birds |
E136036
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Killing Birds |
E136036
|
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: Killing Birds | Statement: [Killing Birds, title, Killing Birds]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Killing Birds Context triple: [Killing Birds, title, Killing Birds]
-
A.
Killing Birds
chosen
"Killing Birds" is a song featured on the album "Carry On."
-
B.
Too Many Birds
"Too Many Birds" is a contemplative indie folk song by Bill Callahan, noted for its sparse arrangement and poetic, introspective lyrics.
-
C.
The Bird
The Bird is a famous oversized bronze bird sculpture by Colombian artist Fernando Botero, exemplifying his signature exaggerated, voluminous style.
-
D.
Vulture
Vulture is a Marvel Comics supervillain, best known as one of Spider-Man’s earliest and recurring adversaries who uses a specialized winged suit to fly and commit crimes.
-
E.
Vulture
Vulture is an online entertainment and culture website known for its in-depth coverage of television, movies, music, and pop culture.
- 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_69c0087dee9881909e3655be88208c01 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05b3dbc6c8190b9e3d81e6ca9eeb8 |
completed | March 22, 2026, 9:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1254fbbf881908b7a3d07f0400387 |
completed | March 23, 2026, 11:34 a.m. |
Created at: March 22, 2026, 4:13 p.m.