Triple
T20232464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Talons of Weng-Chiang |
E495561
|
entity |
| Predicate | featuresCompanion |
P48101
|
FINISHED |
| Object | Leela |
—
|
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: Leela | Statement: [The Talons of Weng-Chiang, featuresCompanion, Leela]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Leela Context triple: [The Talons of Weng-Chiang, featuresCompanion, Leela]
-
A.
Leela
chosen
Leela is a companion of the Fourth Doctor in the classic British science fiction television series Doctor Who.
-
B.
Leela
Leela is the one-eyed, tough yet compassionate spaceship captain from the animated television series "Futurama."
-
C.
Seeta
Seeta is a rapidly growing suburban town and trading center in central Uganda, located along the Kampala–Jinja highway near Mukono.
-
D.
Neela
Neela is a central street racer and love interest in the film "The Fast and the Furious: Tokyo Drift," known for her drifting skills in Tokyo's underground racing scene.
-
E.
Neela
Neela is a prominent commander in the monkey kingdom of Kishkindha in the Indian epic Ramayana, known for his leadership in Rama’s campaign against Ravana.
- 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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66fddafac819089cef4158f5e0ab5 |
completed | April 20, 2026, 6:26 p.m. |
Created at: April 11, 2026, 11:40 p.m.