Triple
T16635511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walter Chang |
E404187
|
entity |
| Predicate | associatedWithCreature |
P36903
|
FINISHED |
| Object | Graboid |
E1224189
|
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: Graboid | Statement: [Walter Chang, associatedWithCreature, Graboid]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graboid Context triple: [Walter Chang, associatedWithCreature, Graboid]
-
A.
Graboid
chosen
A Graboid is a fictional subterranean worm-like monster from the "Tremors" film series, known for hunting prey by sensing ground vibrations.
-
B.
Grabler
Grabler is a surname of likely Germanic origin associated with individuals such as Maria Magdalena Grabler.
-
C.
Blocka
"Blocka" is a hip-hop track by Pusha T known for its dark, aggressive production and hard-edged lyrical style.
-
D.
Grab
Grab is a Southeast Asian super-app company best known for its ride-hailing, food delivery, and digital payments services.
-
E.
de Graft
de Graft is a surname most notably associated with Ghanaian playwright, poet, and educator Joe de Graft.
- 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_69d8838a41f08190b0c3f79c47df5078 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e378e999d48190bff680040dbc883d |
completed | April 18, 2026, 12:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0084b984d081909f76ef874431ff40 |
completed | May 10, 2026, 1:14 p.m. |
Created at: April 10, 2026, 5:17 a.m.