Triple
T16675437
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyaena |
E405204
|
entity |
| Predicate | followedBy |
P78
|
FINISHED |
| Object | Tinderbox |
E405205
|
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: Tinderbox | Statement: [Hyaena, followedBy, Tinderbox]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tinderbox Context triple: [Hyaena, followedBy, Tinderbox]
-
A.
Tinderbox
chosen
Tinderbox is a 1986 post-punk/gothic rock album by Siouxsie and the Banshees, noted for its atmospheric sound and the single "Cities in Dust."
-
B.
The Black Box
The Black Box is a crime novel by Michael Connelly featuring LAPD detective Harry Bosch as he reopens a decades-old murder case first encountered during the 1992 Los Angeles riots.
-
C.
Tristero
Tristero is a mysterious underground postal system and secret organization central to the conspiracy and ambiguity in Thomas Pynchon's novel "The Crying of Lot 49."
-
D.
The Box
"The Box" is a 2019 trap/hip-hop single by Roddy Ricch that became a viral hit and topped the Billboard Hot 100 for multiple weeks.
-
E.
The Box
The Box is an Australian television soap opera produced in the 1970s that became known for its risqué content and behind-the-scenes look at a fictional TV station.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37d6a1960819098c5e3385693a87a |
completed | April 18, 2026, 12:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0091927a408190a612a9ae2fd30d0a |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:19 a.m.